© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16007
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "End" in various contexts, often related to programming or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tend
    -0.39
    memoized
    -0.35
    TagMode
    -0.33
    endforeach
    -0.32
     end
    -0.32
     Dicapai
    -0.32
    Compat
    -0.31
    Tabla
    -0.31
    amoan
    -0.31
     Correspond
    -0.30
    POSITIVE LOGITS
     End
    1.97
    End
    1.73
     Start
    0.94
    Start
    0.93
    getEnd
    0.86
     Side
    0.86
     Endpoint
    0.84
     END
    0.80
     Endo
    0.78
     Ends
    0.74
    Activations Density 0.360%

    No Known Activations