© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12038
    Prev
    Next
    INDEX
    Explanations

    statistical significance and numerical data related to risk assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical data and statistical results in academic and legal documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EditorBrowsable
    -0.39
    Spec
    -0.37
    Barber
    -0.36
     Barber
    -0.36
    degenerate
    -0.35
    Loc
    -0.35
    肉
    -0.34
     stihl
    -0.33
    💈
    -0.33
    content
    -0.32
    POSITIVE LOGITS
    CodeAttribute
    0.55
     AssemblyTitle
    0.54
    AnimationsModule
    0.50
    transQ
    0.48
    ")->
    0.45
     ujednoznacz
    0.44
    prepareStatement
    0.44
    PathVariable
    0.42
     vPvB
    0.41
    enumii
    0.41
    Activations Density 1.005%

    No Known Activations