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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13612
    Prev
    Next
    INDEX
    Explanations

    references to legal sections and citations in regulatory documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.54
     pinulongan
    -0.52
    IntoConstraints
    -0.48
     uLocal
    -0.48
    AnimationsModule
    -0.48
    PreInfinity
    -0.47
     tartalomajánló
    -0.47
    styleable
    -0.46
    urahan
    -0.45
     Anſ
    -0.44
    POSITIVE LOGITS
     nineteen
    0.90
     Nineteen
    0.79
     ۱۹
    0.75
    ۱۹
    0.67
    一九
    0.63
    ⑲
    0.62
     xix
    0.58
     XIX
    0.57
    xix
    0.52
    十九
    0.48
    Activations Density 0.548%

    No Known Activations