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. 20-GEMMASCOPE-RES-16K
    6. 9832
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to various sciences and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -1.12
    .
    -1.03
    -
    -1.03
     
    -1.02
     in
    -0.98
     a
    -0.97
     (
    -0.96
      
    -0.93
     and
    -0.92
     for
    -0.90
    POSITIVE LOGITS
     незавершена
    1.80
     فريبيس
    1.67
    تقاوى
    1.59
    ſelf
    1.58
     Anſ
    1.57
    principalColumn
    1.52
     houſe
    1.51
     متعلقه
    1.49
     Houſe
    1.48
     ſche
    1.47
    Activations Density 1.220%

    No Known Activations