© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    components related to toys and games for children

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

    the word "puzzle" and related puzzle-themed content.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     فريبيس
    -0.49
    MethodManager
    -0.44
    
    -0.43
     مشين
    -0.41
    AsUp
    -0.40
     الحره
    -0.39
    HtmlAttribute
    -0.37
    RTLI
    -0.37
    
    -0.36
     Rptr
    -0.35
    POSITIVE LOGITS
     puzzle
    2.31
     puzzles
    2.09
     Puzzle
    1.88
    puzzle
    1.86
    Puzzle
    1.75
     Puzzles
    1.70
     puzz
    1.64
     rompecabezas
    1.62
     jigsaw
    1.57
     crossword
    1.50
    Activations Density 0.270%

    No Known Activations