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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57323
    Prev
    Next
    INDEX
    Explanations

    HTML table row structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pausal
    -0.61
    WEBPACK
    -0.59
     Kins
    -0.57
     Falco
    -0.56
    ignal
    -0.56
    vey
    -0.56
     hann
    -0.55
    tilizer
    -0.54
     useAuth
    -0.54
     Zay
    -0.54
    POSITIVE LOGITS
    </tr>
    1.25
    </tbody>
    0.96
    Personensuche
    0.96
     "..\..\..\
    0.88
    GEBURTSDATUM
    0.85
     الحره
    0.84
     للاسماء
    0.83
    </tfoot>
    0.83
     AssemblyTitle
    0.75
     pinulongan
    0.75
    Activations Density 0.001%

    No Known Activations