© 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. 35-GEMMASCOPE-RES-16K
    6. 12646
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haupts
    -0.39
     <>",
    -0.39
    ----</
    -0.37
    rungsseite
    -0.37
    เก
    -0.34
     keamanan
    -0.34
     Reihenfolge
    -0.34
    cią
    -0.33
     ModelExpression
    -0.32
    extrémité
    -0.31
    POSITIVE LOGITS
     houſe
    0.57
    IntoConstraints
    0.56
    hrs
    0.55
    StoryboardSegue
    0.54
     lccn
    0.53
     purpoſe
    0.52
     hrs
    0.50
    hours
    0.50
     uhr
    0.50
     Hours
    0.49
    Activations Density 0.143%

    No Known Activations