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. 13414
    Prev
    Next
    INDEX
    Explanations

    statements of existence or presence

    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
    その
    -0.70
    Valid
    -0.67
    Success
    -0.64
    お
    -0.62
     censi
    -0.60
    Enabled
    -0.56
    Empty
    -0.56
    お手
    -0.56
    ward
    -0.55
    wards
    -0.55
    POSITIVE LOGITS
     also
    1.20
     indeed
    1.15
     actually
    1.14
     certainly
    1.05
     now
    1.02
     definitely
    1.02
     always
    1.00
     not
    0.99
     still
    0.98
     probably
    0.98
    Activations Density 1.034%

    No Known Activations