© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships involving variables and equations

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

    mathematical and scientific notation, particularly equations, variables, and technical terms in academic or scientific text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mathematical and scientific notation with variables and mathematical symbols.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.79
     utafitiHapana
    -0.77
    AndEndTag
    -0.75
     hlavy
    -0.71
     mijne
    -0.71
    LookAnd
    -0.71
     feroit
    -0.70
    MessageTagHelper
    -0.70
     ब्रेकडाउन
    -0.70
     estekak
    -0.68
    POSITIVE LOGITS
     parse
    0.56
    parse
    0.54
     apt
    0.47
     Bat
    0.46
     Sam
    0.46
     nap
    0.45
    PostMapping
    0.45
     ob
    0.45
    Parsed
    0.44
     pun
    0.44
    Activations Density 1.394%

    No Known Activations