© 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. 17-GEMMASCOPE-RES-16K
    6. 1503
    Prev
    Next
    INDEX
    Explanations

    time intervals and frequencies of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     annual
    -0.79
     daily
    -0.76
     Daily
    -0.74
     Annual
    -0.74
    Daily
    -0.73
    daily
    -0.73
    Annual
    -0.71
    annual
    -0.70
     täglichen
    -0.70
    AnchorStyles
    -0.67
    POSITIVE LOGITS
     متعلقه
    0.74
    씩
    0.74
     until
    0.64
     since
    0.62
    Until
    0.58
     scolas
    0.58
     mellom
    0.57
     scolaire
    0.55
     GenerationType
    0.55
     thereafter
    0.54
    Activations Density 0.303%

    No Known Activations