© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 859
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific measurements and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.69
     INTERESAR
    -0.60
     يتيمه
    -0.57
    findpost
    -0.55
     ویکی‌پدی
    -0.51
    ambién
    -0.50
    AndEndTag
    -0.50
     nonUne
    -0.49
    eramente
    -0.47
     Infórmanos
    -0.46
    POSITIVE LOGITS
    ​,
    0.45
    */,
    0.45
    》,
    0.45
    “,
    0.44
     propOrder
    0.44
     »,
    0.43
    :,
    0.42
    /,
    0.42
    tagext
    0.42
     */,
    0.42
    Activations Density 1.673%

    No Known Activations