© 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. 15-GEMMASCOPE-RES-16K
    6. 1301
    Prev
    Next
    INDEX
    Explanations

    words highlighting essential qualities or components necessary for health and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.83
    InitVars
    -0.78
    횟
    -0.77
    TagMode
    -0.76
     fatos
    -0.75
     חיצוניים
    -0.74
     oprot
    -0.72
    SerializedSize
    -0.72
    XmlType
    -0.72
    afficheront
    -0.71
    POSITIVE LOGITS
    essen
    0.89
     ESS
    0.74
    SBS
    0.73
    Essen
    0.73
    SSF
    0.73
     OnDestroy
    0.72
    Portail
    0.71
     SSC
    0.71
    ESS
    0.69
     Kessel
    0.69
    Activations Density 0.088%

    No Known Activations