© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4342
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific input/output notations or prefixes in coding contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ―――――
    -1.05
     ་་
    -1.00
     ――――――――
    -0.89
     Theſe
    -0.82
    EMOS
    -0.78
    enumi
    -0.78
     Monfieur
    -0.77
     doubtnut
    -0.74
     Smarty
    -0.74
     Paloma
    -0.73
    POSITIVE LOGITS
     IN
    1.73
    IN
    1.71
    In
    1.48
    in
    1.48
     In
    1.44
    getIn
    1.23
     isIn
    1.00
    inb
    0.91
     in
    0.90
    INS
    0.86
    Activations Density 0.171%

    No Known Activations