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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2783
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.88
    ,
    -0.84
     and
    -0.84
     here
    -0.81
     car
    -0.78
     in
    -0.78
     your
    -0.77
     as
    -0.77
     to
    -0.77
     for
    -0.76
    POSITIVE LOGITS
     auffi
    0.93
     فريبيس
    0.90
     plufieurs
    0.90
     InputDecoration
    0.88
     ainfi
    0.87
     EconPapers
    0.86
     PTS
    0.85
     TTS
    0.85
     itſelf
    0.84
     Anſ
    0.83
    Activations Density 0.003%

    No Known Activations