© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13323
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to characters, actions, and interactions in a storyline

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

    Comes before "saw" or "went."

    np_acts-logits-general · gemini-2.0-flash

    seeing or acting after pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrate
    -0.50
     movilidad
    -0.46
     migrated
    -0.46
     Move
    -0.44
    move
    -0.44
    Move
    -0.44
     mobility
    -0.44
     migrate
    -0.42
    Mobility
    -0.42
     migration
    -0.42
    POSITIVE LOGITS
    ImageContext
    0.82
     stops
    0.80
     stopping
    0.79
    featureID
    0.78
     encounters
    0.78
    httphttps
    0.75
     pausing
    0.73
     Stops
    0.73
     encounter
    0.71
     encountering
    0.71
    Activations Density 0.462%

    No Known Activations