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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    quantities and comparisons involving size or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.65
    HideFlags
    -0.60
    uitable
    -0.56
    __':
    
    -0.53
    PreInfinity
    -0.51
    pañas
    -0.49
    깥
    -0.49
    __':
    -0.49
    auré
    -0.48
     Roskov
    -0.48
    POSITIVE LOGITS
     sized
    1.23
     sounding
    1.18
     looking
    1.14
     priced
    1.13
     shaped
    0.98
     smelling
    0.97
     LOOKING
    0.97
     minded
    0.95
    looking
    0.95
     valued
    0.92
    Activations Density 0.704%

    No Known Activations