© 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. 7695
    Prev
    Next
    INDEX
    Explanations

    words related to electro technologies or devices

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

    following "electro" (electricity/kinetics)

    np_acts-logits-general · gemini-2.0-flash

    electro- followed by science/technical terms

    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
     Roskov
    -0.67
    ก่
    -0.63
    EndContext
    -0.59
    )++;
    -0.59
    Ranks
    -0.58
     kanya
    -0.58
    SequentialGroup
    -0.58
     IMA
    -0.56
     Himal
    -0.55
     Bourgoin
    -0.55
    POSITIVE LOGITS
    MLLoader
    0.61
    setupUi
    0.60
     keres
    0.53
    
    0.52
    providedIn
    0.49
    PMailer
    0.49
    ecma
    0.49
    AHAN
    0.48
     CURIAM
    0.48
     remaining
    0.46
    Activations Density 0.152%

    No Known Activations