© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 750
    Prev
    Next
    INDEX
    Explanations

    terms related to program configuration and computation

    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
     Audiodateien
    -0.40
    LookAnd
    -0.39
    RectangleBorder
    -0.38
    sizeCache
    -0.36
     Trouver
    -0.34
     pilote
    -0.34
    InputBorder
    -0.33
    shoulder
    -0.32
     adet
    -0.32
     escol
    -0.30
    POSITIVE LOGITS
     للمعارف
    0.58
    ppe
    0.50
    dy
    0.49
    ς
    0.49
    ding
    0.48
    mos
    0.48
    cting
    0.48
    mals
    0.48
     Wikimedijinoj
    0.48
    ment
    0.47
    Activations Density 0.278%

    No Known Activations