© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91235
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or love for activities and experiences

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

    liking and loving things

    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
     kasarigan
    -0.77
    الإنجليزية
    -0.70
     autorytatywna
    -0.62
    providedIn
    -0.62
    Kanpo
    -0.57
    bootstrapcdn
    -0.57
    WebServlet
    -0.57
    +#+#
    -0.56
    Autoritní
    -0.55
    PRNewswire
    -0.55
    POSITIVE LOGITS
     dearly
    0.47
     buying
    0.39
     seeing
    0.39
     eating
    0.37
     discussing
    0.36
     watching
    0.36
     purchasing
    0.35
     getting
    0.35
     renting
    0.35
     reading
    0.34
    Activations Density 0.028%

    No Known Activations