Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11613
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal proceedings, particularly settlements and plea agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msford
    -0.42
    WireFormatLite
    -0.41
     yoksa
    -0.40
    jalanan
    -0.39
    Джерела
    -0.39
    getMenuInflater
    -0.38
    XmlAccessorType
    -0.38
    鑑
    -0.38
    EndContext
    -0.38
    ffilm
    -0.38
    POSITIVE LOGITS
     settlement
    0.85
     Settlement
    0.80
    Settlement
    0.76
     settlements
    0.74
     settle
    0.74
    settlement
    0.73
     SETTLE
    0.72
     settling
    0.71
    settle
    0.71
    Settle
    0.68
    Activations Density 0.832%

    No Known Activations