© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 538
    Prev
    Next
    INDEX
    Explanations

    mentions of licensing and open-source implementations

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

    mentions of high-quality software implementations and related technologies

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

    3 . within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     &___
    -0.80
    WireFormatLite
    -0.80
    Geplaatst
    -0.75
    SequentialGroup
    -0.73
    rungsseite
    -0.72
    IntoConstraints
    -0.72
    ponses
    -0.71
    GEBURTSDATUM
    -0.66
    RegistryLite
    -0.66
     onCreateView
    -0.66
    POSITIVE LOGITS
    <h2>
    0.54
    )}.
    0.51
    انتهای
    0.51
    `).
    0.50
    AuthGuard
    0.48
    ')}}">
    0.48
    .)}
    0.48
    <!--[
    0.48
    <tr>
    0.48
    ]='\
    0.48
    Activations Density 0.013%

    No Known Activations