© 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. 14329
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rulings and legislation

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

    phrases indicating state-level laws, regulations, or geographic references to specific US states.

    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
     crossorigin
    -0.46
    ผ
    -0.40
    parsedMessage
    -0.40
    SourceChecksum
    -0.40
    OGND
    -0.40
    -£
    -0.40
     mondial
    -0.37
    期刊论文
    -0.35
     kropp
    -0.35
     Kelurahan
    -0.33
    POSITIVE LOGITS
     states
    1.44
     California
    1.41
     Pennsylvania
    1.37
     Illinois
    1.32
     Florida
    1.30
     Ohio
    1.29
    California
    1.27
    states
    1.27
     States
    1.26
     Texas
    1.26
    Activations Density 0.921%

    No Known Activations