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. 4226
    Prev
    Next
    INDEX
    Explanations

    references to legal statutes and regulations

    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
    ьаж
    -0.50
     convince
    -0.45
    脚注の使い方
    -0.44
    وصل
    -0.44
     persuaded
    -0.42
     חיצוניים
    -0.41
    Report
    -0.41
    디오
    -0.41
     gefe
    -0.40
    ელ
    -0.40
    POSITIVE LOGITS
     provisions
    1.13
     prohibiting
    1.04
     prohibits
    1.02
     forbids
    0.95
     provision
    0.93
     prohibit
    0.92
     PROVISIONS
    0.89
     forbid
    0.88
    provision
    0.87
     Provisions
    0.86
    Activations Density 0.703%

    No Known Activations