© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7159
    Prev
    Next
    INDEX
    Explanations

    references to fish and fishing activities

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

    fish or fishing

    np_acts-logits-general · gemini-2.0-flash

    fish and fishing

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCompany
    -0.52
     Alhambra
    -0.42
     möge
    -0.42
     ***!
    -0.41
    ampton
    -0.40
     kesadaran
    -0.40
     onCreateView
    -0.39
     regole
    -0.39
     berço
    -0.39
     vrijwilli
    -0.39
    POSITIVE LOGITS
     fish
    2.02
     Fish
    1.92
    Fish
    1.89
     fishing
    1.85
     FISH
    1.79
     fished
    1.77
    fish
    1.77
    FISH
    1.77
     Fishing
    1.75
    Fishing
    1.71
    Activations Density 0.127%

    No Known Activations