© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5903
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured timing and planning in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prisonniers
    -0.56
    MigrationBuilder
    -0.56
     wikipagina
    -0.53
    IsMutable
    -0.52
     للمعارف
    -0.51
    kháu
    -0.51
     queſta
    -0.49
    rungsseite
    -0.47
    PhysRev
    -0.46
     gebo
    -0.46
    POSITIVE LOGITS
     afternoon
    1.01
     morning
    0.95
     evening
    0.94
     overnight
    0.81
    morning
    0.79
    afternoon
    0.78
    evening
    0.77
     midday
    0.75
     hours
    0.74
     lunch
    0.72
    Activations Density 0.405%

    No Known Activations