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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9989
    Prev
    Next
    INDEX
    Explanations

    instances of political resistance and legal proceedings

    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
     CWE
    -0.57
     gainera
    -0.51
     ExecuteAsync
    -0.48
    出版年
    -0.45
    Rüyada
    -0.45
     AssemblyTitle
    -0.44
     stethoscope
    -0.44
    ulta
    -0.43
    ngrx
    -0.42
    AppCompat
    -0.41
    POSITIVE LOGITS
     refusal
    2.30
     resistance
    2.13
     refus
    2.07
     refused
    2.00
     resist
    1.98
     refusing
    1.97
     resisted
    1.95
     resisting
    1.94
     refuse
    1.93
     rejection
    1.89
    Activations Density 0.746%

    No Known Activations