© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    references to characters or personas associated with unique abilities or transformations in a story

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

    Teenage Mutant Ninja Turtles

    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
    DataAnnotations
    -0.63
    IntoConstraints
    -0.58
    jsii
    -0.57
    indd
    -0.53
    windowFixed
    -0.51
    Cactus
    -0.50
    setupUi
    -0.46
     resourceCulture
    -0.46
    smithy
    -0.45
    Източници
    -0.45
    POSITIVE LOGITS
     ninja
    0.63
     mutagen
    0.63
     Teenage
    0.60
     Ninja
    0.56
     Turtles
    0.56
    Teenage
    0.55
     mutant
    0.55
     Mutant
    0.53
    Mutation
    0.51
     ninjas
    0.51
    Activations Density 0.038%

    No Known Activations