© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103985
    Prev
    Next
    INDEX
    Explanations

    HTML tags and markup elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ↵↵
    -0.35
     Pedersen
    -0.33
     Fach
    -0.33
     nativo
    -0.32
    בן
    -0.32
    x
    -0.31
    loggedIn
    -0.31
    ↵
    -0.31
    CGSize
    -0.31
     Super
    -0.30
    POSITIVE LOGITS
    存于互联网档案馆
    0.81
    featureID
    0.71
    __(/*!
    0.70
     >=",
    0.69
     ExecuteAsync
    0.67
    <unused14>
    0.67
    [@BOS@]
    0.67
    <unused47>
    0.67
    <unused28>
    0.67
    <unused8>
    0.67
    Activations Density 0.045%

    No Known Activations