© 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. 0-GEMMASCOPE-RES-16K
    11. 8096
    Prev
    Next
    INDEX
    Explanations

    references to variable names and properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ones
    -0.46
     things
    -0.41
     pieces
    -0.40
     versions
    -0.38
     areas
    -0.37
     items
    -0.36
    <_>
    -0.35
     elements
    -0.35
     groups
    -0.34
     kinds
    -0.34
    POSITIVE LOGITS
    rates
    1.05
    cells
    1.04
    names
    1.04
    ients
    1.03
     épaules
    1.02
    ports
    1.02
    habits
    1.00
    waits
    0.99
    ROOMS
    0.99
    papers
    0.99
    Activations Density 1.547%

    No Known Activations