© 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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2260
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural and entertainment topics, particularly relating to sports and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.69
    tagHelperRunner
    -0.63
     ivelany
    -0.55
    :][
    -0.54
    aarrggbb
    -0.54
    Identyfik
    -0.54
     itinéraires
    -0.53
     lenker
    -0.52
    findpost
    -0.49
    énario
    -0.49
    POSITIVE LOGITS
     America
    0.35
     journalism
    0.33
     democracy
    0.32
     industry
    0.31
     culture
    0.31
     advancement
    0.30
     maxX
    0.30
    というもの
    0.29
     humanity
    0.29
     Romania
    0.29
    Activations Density 0.647%

    No Known Activations