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

    Neuronpedia

    Jacobian LensNEW
    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. 7192
    Prev
    Next
    INDEX
    Explanations

    legal terminology or references in judicial documents

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

    legal document structural elements and formatting markers like case citations, punctuation, and numbers.

    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
    SourceChecksum
    -0.62
    +#+#
    -0.56
    ValueStyle
    -0.54
     resourceCulture
    -0.52
    uxxxx
    -0.52
    LookAnd
    -0.51
    @[+][
    -0.50
     <<<<<<<<<<<<<<
    -0.49
    extAlignment
    -0.49
     ModelExpression
    -0.47
    POSITIVE LOGITS
    itness
    0.38
    navigationItem
    0.36
    携
    0.35
     Currently
    0.35
    Rape
    0.34
     pendiente
    0.34
    Current
    0.34
    Vern
    0.34
     demas
    0.33
    攜
    0.33
    Activations Density 1.610%

    No Known Activations