© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13036
    Prev
    Next
    INDEX
    Explanations

    specific game-related jargon and terminology, particularly concerning character classes and abilities

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

    Game-related terms/actions

    np_acts-logits-general · gemini-2.0-flash

    weapon type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.55
    بوابة
    -0.55
    uterte
    -0.54
     Destination
    -0.49
     CHIP
    -0.48
     diem
    -0.48
    DockStyle
    -0.48
     testigos
    -0.48
    例句
    -0.47
    InputBorder
    -0.46
    POSITIVE LOGITS
     maxed
    0.84
     lvl
    0.78
     melee
    0.71
     builds
    0.70
     leveling
    0.68
     level
    0.67
     wielding
    0.67
    Lvl
    0.65
     ranged
    0.65
     equip
    0.64
    Activations Density 0.316%

    No Known Activations