© 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. 0-GEMMASCOPE-RES-16K
    6. 10009
    Prev
    Next
    INDEX
    Explanations

    references to cruise-related activities and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.60
    setVerticalGroup
    -0.57
    Ӕ
    -0.57
    MLLoader
    -0.55
    )_/¯
    -0.55
    phazard
    -0.54
    estacks
    -0.53
    imentos
    -0.51
    iness
    -0.50
    motor
    -0.50
    POSITIVE LOGITS
     cruise
    0.57
     crucero
    0.50
     panic
    0.47
    <>());
    0.44
     cru
    0.44
    ']));
    0.40
     StatefulWidget
    0.40
    <>();
    0.39
     Jus
    0.39
     traffic
    0.36
    Activations Density 0.212%

    No Known Activations