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. 9948
    Prev
    Next
    INDEX
    Explanations

    references to financial contributions or fundraising activities

    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
    SerializedSize
    -0.69
     restTemplate
    -0.66
     newBuilder
    -0.64
    invokeLater
    -0.64
     fieldNum
    -0.64
    DataAnnotations
    -0.63
    FieldBuilder
    -0.62
     Normdatei
    -0.62
    interopRequire
    -0.60
    Referencies
    -0.59
    POSITIVE LOGITS
     proceeds
    1.52
     funds
    1.22
     Proceeds
    1.17
     monies
    1.03
     money
    1.02
    funds
    0.99
     Funds
    0.95
     profits
    0.93
    Funds
    0.91
    ceeds
    0.88
    Activations Density 0.333%

    No Known Activations