Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8521
    Prev
    Next
    INDEX
    Explanations

    numerical data and calculations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.37
     الرخصة
    -0.36
    ape
    -0.35
    相
    -0.34
    ----</
    -0.33
    didSet
    -0.32
    Autoritní
    -0.31
    LayoutPanel
    -0.31
    getResource
    -0.30
    ComponentModel
    -0.30
    POSITIVE LOGITS
    enderror
    0.60
     فريبيس
    0.57
    StructEnd
    0.54
     onAnimation
    0.52
     houſe
    0.51
    neſs
    0.51
     itſelf
    0.50
     myſelf
    0.50
    rzost
    0.50
     perſon
    0.48
    Activations Density 1.313%

    No Known Activations