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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6909
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hull" and its variations in the context of sports or geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hull followed by om

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.61
    المكان
    -0.57
    Datuak
    -0.57
     Spie
    -0.56
     ***!
    -0.56
    wpi
    -0.56
     ALO
    -0.53
    +#+#
    -0.52
     RZ
    -0.50
    ▹
    -0.50
    POSITIVE LOGITS
     Hull
    2.34
    Hull
    2.23
     hull
    1.89
    hull
    1.83
     hulls
    1.48
    Hul
    0.76
    hul
    0.76
     Hul
    0.75
     hul
    0.69
     coque
    0.68
    Activations Density 0.001%

    No Known Activations