Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 114930
    Prev
    Next
    INDEX
    Explanations

    references to images or figures in technical documentation

    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
    ftagPool
    -0.58
     transfieras
    -0.47
    ActionCreators
    -0.47
    routeProvider
    -0.45
    stylers
    -0.44
    BSITE
    -0.42
    Diwedd
    -0.42
    archiviato
    -0.41
     كورة
    -0.41
     nonUne
    -0.41
    POSITIVE LOGITS
     screenshots
    0.53
     screenshot
    0.48
     defaultstate
    0.45
    ![](
    0.44
    <b>
    0.43
     Screenshots
    0.43
     gifs
    0.42
     GIFs
    0.42
    naeus
    0.41
    texttt
    0.41
    Activations Density 0.238%

    No Known Activations