© 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. 31-GEMMASCOPE-RES-16K
    6. 8453
    Prev
    Next
    INDEX
    Explanations

    references to judicial or formal procedures and legal terminologies

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

    opening clauses of quoted or formal statements.

    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
    MessageTagHelper
    -0.77
    ########.
    -0.73
     kasarigan
    -0.73
     ModelExpression
    -0.72
    adaptiveStyles
    -0.71
     AssemblyTitle
    -0.69
    msgTypes
    -0.67
    MigrationBuilder
    -0.66
     protoimpl
    -0.65
    rungsseite
    -0.65
    POSITIVE LOGITS
     traditional
    0.45
     Groß
    0.45
     Brown
    0.45
     Wiel
    0.44
     Alfred
    0.43
     Enkel
    0.42
    table
    0.42
     David
    0.42
     common
    0.42
     Randy
    0.41
    Activations Density 2.236%

    No Known Activations