© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1366
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical constructs and proofs, particularly involving roots and sums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical terms and symbols related to root systems, algebraic structures, and mathematical computations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mathematical notation for linear combinations and set relations—expressions with addition/subtraction and membership/exclusion—especially in formal algebraic decompositions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    mathematical expressions involving sums of roots or indexed variables in formal mathematical notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档
    -0.36
    deleteAll
    -0.36
    barrier
    -0.36
     Stakes
    -0.36
    Barrier
    -0.35
     Barrier
    -0.35
     barrier
    -0.34
    Пер
    -0.33
     Grounds
    -0.33
    astrous
    -0.33
    POSITIVE LOGITS
    rawDesc
    0.63
     combinations
    0.57
     виправивши
    0.54
     Majefty
    0.53
     pouvoit
    0.52
    EndContext
    0.50
    migrationBuilder
    0.48
    ſelves
    0.48
     combos
    0.48
     offsets
    0.47
    Activations Density 0.755%

    No Known Activations