© 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. 9-GEMMASCOPE-RES-131K
    11. 55716
    Prev
    Next
    INDEX
    Explanations

    references to different types of puzzles and games

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

    puzzles, puzzling, and confused

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTERS
    -0.45
    INCREF
    -0.44
    Rptr
    -0.43
     Ced
    -0.42
     Rptr
    -0.39
     nej
    -0.39
     lượt
    -0.37
    from
    -0.35
     vigueur
    -0.35
    venidos
    -0.35
    POSITIVE LOGITS
     puzzle
    2.19
     Puzzle
    2.05
    puzzle
    1.96
     puzzles
    1.90
    Puzzle
    1.87
     Puzzles
    1.70
     puzz
    1.43
     rompecabezas
    1.24
     puzzling
    1.11
    ZZLE
    1.09
    Activations Density 0.003%

    No Known Activations