© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 17818
    Prev
    Next
    INDEX
    Explanations

    conversations centered around brewing or fermenting alcoholic beverages

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

    suggestions for experimentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passengers
    -0.37
    tritts
    -0.34
     Обо
    -0.34
     corridors
    -0.33
     claw
    -0.33
    ArrowToggle
    -0.33
    claw
    -0.33
     commuters
    -0.33
     yawning
    -0.33
     mobility
    -0.32
    POSITIVE LOGITS
     experimentation
    0.93
     experimenting
    0.91
     experiment
    0.85
    Experiment
    0.84
    experiment
    0.83
     Experiment
    0.82
     experim
    0.82
     experiments
    0.81
     EXPERIMENT
    0.81
     experimenter
    0.78
    Activations Density 0.045%

    No Known Activations