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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10278
    Prev
    Next
    INDEX
    Explanations

    code-related structures and function definitions

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

    function or method declarations and their surrounding signature/annotation markers in source code.

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

    function or method declarations in source code.

    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
    CppMethod
    -0.59
     }{@
    -0.56
    帖最后由
    -0.54
    featureID
    -0.54
    makeConstraints
    -0.52
    LookAnd
    -0.50
    verifyException
    -0.49
     <>",
    -0.49
    numerusform
    -0.48
    execSQL
    -0.48
    POSITIVE LOGITS
     الاطلاع
    0.43
    يميديا
    0.40
    <?
    0.39
     کیلوم
    0.38
    SuspendLayout
    0.35
    '))
    0.35
     nahilalakip
    0.35
    Билгалдахарш
    0.34
    DialogResult
    0.34
     /**
    0.34
    Activations Density 0.097%

    No Known Activations