© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7146
    Prev
    Next
    INDEX
    Explanations

    dates, times, and deadlines related to events or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poursuite
    -0.35
     siento
    -0.35
     islas
    -0.35
    efois
    -0.35
     toiture
    -0.34
     fronteras
    -0.34
    wußt
    -0.33
     Tätigkeit
    -0.33
    pośred
    -0.32
     piacevole
    -0.32
    POSITIVE LOGITS
     ujednoznacz
    0.68
     disambiguazione
    0.63
     hust
    0.56
     punt
    0.54
     nahilalakip
    0.53
    apnews
    0.52
    botto
    0.52
     breathless
    0.50
    chief
    0.50
     unw
    0.50
    Activations Density 0.176%

    No Known Activations