© 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. 11314
    Prev
    Next
    INDEX
    Explanations

    references to the term "ZA" or related variations indicating a specific entity or concept

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

    Followed by "a" and other letters

    np_acts-logits-general · gemini-2.0-flash

    za followed by names or places

    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
    esterno
    -0.51
     oiseaux
    -0.46
    cznego
    -0.45
    grafia
    -0.45
    withId
    -0.44
     Wrench
    -0.44
     pianta
    -0.44
     Rashford
    -0.44
    findElement
    -0.44
     hati
    -0.43
    POSITIVE LOGITS
    رشف
    0.71
     BoxDecoration
    0.70
    ScopeManager
    0.66
     lenker
    0.64
     bpy
    0.56
    wound
    0.55
    utory
    0.55
    ActionCreators
    0.54
     anecd
    0.53
    ++]=
    0.52
    Activations Density 0.031%

    No Known Activations