© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6147
    Prev
    Next
    INDEX
    Explanations

    terms associated with varying thicknesses and densities, particularly in relation to "thin" and "fat" materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "fat" or "thin"

    np_acts-logits-general · gemini-2.0-flash

    fat or thin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.89
    oredCriteria
    -0.82
    WebServlet
    -0.76
    ThroughAttribute
    -0.76
    abestanden
    -0.73
     Efq
    -0.71
    RTLD
    -0.71
     تانيه
    -0.70
     Shakspeare
    -0.69
    קישורים
    -0.69
    POSITIVE LOGITS
    ness
    0.70
     margin
    0.60
    ening
    0.58
    tening
    0.57
    ets
    0.55
    est
    0.55
     margins
    0.54
    uity
    0.54
     fit
    0.52
    ener
    0.51
    Activations Density 0.123%

    No Known Activations