© 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. 6934
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to proofs and theorems

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

    mathematical or scientific terminology and notation.

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

    formal mathematical discourse—statements introducing theorems, proofs, problems, and equation-heavy content in academic writing.

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

    mathematical and academic language describing proofs, theorems, problems, and formal demonstrations.

    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
    AddHtmlAttribute
    -0.55
    WebElementEntity
    -0.53
     <>",
    -0.50
    LookAnd
    -0.49
     يتيمه
    -0.49
    脚注の使い方
    -0.47
    허
    -0.46
     Савезне
    -0.45
    tonode
    -0.45
    uxxxx
    -0.45
    POSITIVE LOGITS
    stdc
    0.66
    etCode
    0.46
     mathematical
    0.43
    yntaxException
    0.43
     mathematics
    0.42
     sympy
    0.42
     math
    0.41
     mathematicians
    0.40
     matemática
    0.40
    Билгалдахарш
    0.39
    Activations Density 2.706%

    No Known Activations