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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1628
    Prev
    Next
    INDEX
    Explanations

    structured data, including tables and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.56
    mazione
    -0.50
     contextLoads
    -0.48
     Martin
    -0.48
    jaan
    -0.45
    groupby
    -0.45
    http
    -0.45
     mapStateToProps
    -0.44
    er
    -0.43
    Martin
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.74
     للاسماء
    0.74
     ModelExpression
    0.66
    ècie
    0.65
    קישורים
    0.63
    SourceChecksum
    0.62
     }))
    0.60
     surla
    0.58
    ⓘ
    0.57
    </tfoot>
    0.57
    Activations Density 0.699%

    No Known Activations