© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5405
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure, particularly focusing on function definitions and array manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ment
    -0.58
     ver
    -0.57
     N
    -0.55
     direct
    -0.55
     
    -0.53
     El
    -0.52
     R
    -0.50
    <eos>
    -0.50
     only
    -0.49
     court
    -0.49
    POSITIVE LOGITS
     Anſ
    0.98
     myſelf
    0.95
     Monfieur
    0.92
     purpoſe
    0.91
     Efq
    0.90
    ArgsConstructor
    0.89
     auffi
    0.86
     ſever
    0.83
     ſtate
    0.83
     Majefty
    0.82
    Activations Density 0.419%

    No Known Activations