© 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. 11305
    Prev
    Next
    INDEX
    Explanations

    data structures or identifiers typically associated with programming or database contexts

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

    Followed by numbers after a hyphen

    np_acts-logits-general · gemini-2.0-flash

    UUIDs and identifiers

    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
     désolés
    -0.52
    writeFieldEnd
    -0.50
    ioen
    -0.48
    writeField
    -0.47
    TokenNameRPAREN
    -0.47
     gerak
    -0.45
    ainya
    -0.45
     metrów
    -0.45
    weer
    -0.44
     he
    -0.44
    POSITIVE LOGITS
     Diakses
    0.67
    GeoNames
    0.66
    OGND
    0.62
     оригіналу
    0.59
    /***/
    0.59
    RepeatedField
    0.56
    下载附件
    0.56
     typelib
    0.56
    IconModule
    0.56
    FieldBuilder
    0.55
    Activations Density 0.132%

    No Known Activations