© 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. 18-GEMMASCOPE-RES-16K
    11. 14289
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names, companies, and brands

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

    Unusual or misspelled words

    np_acts-logits-general · gemini-2.0-flash

    Gas chromatographic evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.59
    paged
    -0.57
    nolo
    -0.57
    سجيلات
    -0.56
    IVERY
    -0.56
    cknowled
    -0.56
    igenous
    -0.55
     newState
    -0.55
     IBRARY
    -0.55
    asive
    -0.54
    POSITIVE LOGITS
     بيها
    0.74
    Sucesor
    0.71
    esModule
    0.66
    олові
    0.66
     '\\;'
    0.62
    NewUrlParser
    0.60
     للاسماء
    0.59
    tagHelperRunner
    0.56
    ftagPool
    0.54
    AsUp
    0.53
    Activations Density 0.064%

    No Known Activations