© 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. 10648
    Prev
    Next
    INDEX
    Explanations

    sequences of commands or actions relevant to gameplay instruction

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

    Video game levels, quests, bosses, or difficulty

    np_acts-logits-general · gemini-2.0-flash

    game missions or challenges

    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
     pama
    -0.55
    SharedDtor
    -0.54
     FormControl
    -0.53
    titleMargin
    -0.50
     Unidos
    -0.50
    WidgetItem
    -0.47
    šta
    -0.47
     navegando
    -0.46
    WebServlet
    -0.46
    AutoresizingMask
    -0.46
    POSITIVE LOGITS
     mission
    1.09
     missions
    1.07
     boss
    1.00
     challenge
    0.90
     quests
    0.90
     challenges
    0.88
     bosses
    0.87
     challenging
    0.84
     difficulty
    0.84
     map
    0.84
    Activations Density 0.195%

    No Known Activations