© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12644
    Prev
    Next
    INDEX
    Explanations

    references to word puzzles, specifically crossword puzzles

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

    puzzles and solving them

    np_acts-logits-general · gemini-2.0-flash

    puzzle solving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragamo
    -0.55
    antMatchers
    -0.53
     caries
    -0.52
     Yamato
    -0.52
    vernote
    -0.51
     breeches
    -0.50
    EMT
    -0.50
     Rok
    -0.49
     polvere
    -0.49
    govina
    -0.48
    POSITIVE LOGITS
     puzzle
    1.80
     puzzles
    1.66
     Puzzle
    1.55
    puzzle
    1.44
    Puzzle
    1.42
     Puzzles
    1.37
     solve
    1.37
     solving
    1.31
     puzz
    1.31
     clues
    1.27
    Activations Density 0.210%

    No Known Activations