© 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. 6427
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court proceedings

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

    legal case citations and formal legal document references.

    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
    достатки
    -0.71
    raszamy
    -0.62
     NSCoder
    -0.61
    ConstraintMaker
    -0.61
    YGON
    -0.57
    Autoritní
    -0.57
    stood
    -0.56
    стоинства
    -0.56
    @[+][
    -0.55
    vábbi
    -0.55
    POSITIVE LOGITS
    withstanding
    1.18
    которые
    0.93
    giveness
    0.76
    theless
    0.75
    itudinal
    0.67
    tably
    0.62
    fraid
    0.62
    دواج
    0.61
    sterious
    0.60
    viembre
    0.56
    Activations Density 2.046%

    No Known Activations