Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13736
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics and item crafting in a gaming context

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

    game progress or achievements

    np_acts-logits-general · gemini-2.0-flash

    game leveling and unlocks

    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
     виправивши
    -0.81
     مرئيه
    -0.80
    GraphicsUnit
    -0.79
    PerformLayout
    -0.79
    ViewImports
    -0.72
    abestanden
    -0.70
     الحره
    -0.69
     дописавши
    -0.68
     intptr
    -0.67
    RegressionTest
    -0.66
    POSITIVE LOGITS
     rare
    0.86
     unlock
    0.84
     level
    0.83
     rarity
    0.82
     unlocked
    0.81
     unlocks
    0.78
     leveling
    0.77
     Rare
    0.77
    level
    0.77
     Level
    0.77
    Activations Density 0.303%

    No Known Activations