© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 683
    Prev
    Next
    INDEX
    Explanations

    the modal verb "can" indicating possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.90
    WriteTagHelper
    -0.85
    ThroughAttribute
    -0.77
    principalTable
    -0.76
    writeFieldEnd
    -0.73
    EDEFAULT
    -0.71
    s
    -0.70
    rrggbb
    -0.69
     kunna
    -0.68
    UserScript
    -0.68
    POSITIVE LOGITS
     sometimes
    0.91
     easily
    0.89
     often
    0.76
    opies
    0.75
     be
    0.74
     certainly
    0.73
     also
    0.73
    isters
    0.69
     vary
    0.65
     facilement
    0.65
    Activations Density 0.283%

    No Known Activations