© 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. 8-GEMMASCOPE-RES-16K
    6. 6969
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and types in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ("]");
    -0.49
     Achter
    -0.49
    dirig
    -0.47
    fflush
    -0.47
     guste
    -0.47
    ercito
    -0.47
    nante
    -0.46
    gog
    -0.46
    oval
    -0.46
    fris
    -0.45
    POSITIVE LOGITS
     GenerationType
    1.22
    +#+#
    1.14
    AutoScale
    1.06
    providedIn
    1.00
    GenerationType
    0.95
     jsPsych
    0.94
    gdx
    0.91
    WindowConstants
    0.89
    CloseOperation
    0.82
    RequestMethod
    0.81
    Activations Density 0.018%

    No Known Activations