© 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. 4891
    Prev
    Next
    INDEX
    Explanations

    results and their interpretations in research contexts

    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
    MemoryWarning
    -0.74
     defaultstate
    -0.71
    tvguidetime
    -0.67
    IMPORTED
    -0.66
     ویکی‌پدیا
    -0.64
    Bibliograf
    -0.61
     виправивши
    -0.61
     morire
    -0.59
    IntoConstraints
    -0.59
    География
    -0.58
    POSITIVE LOGITS
     results
    1.12
     Results
    1.00
    Results
    0.94
     result
    0.93
     outcomes
    0.84
    results
    0.84
     RESULTS
    0.84
     résultats
    0.81
     resultados
    0.80
     outcome
    0.77
    Activations Density 0.438%

    No Known Activations