© 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. 12727
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate factors influencing outcomes or decisions

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

    preceding "factor" or "factors"

    np_acts-logits-general · gemini-2.0-flash

    deciding factors

    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
    StoryboardSegue
    -0.64
     Reverso
    -0.62
    出版年
    -0.62
    DTD
    -0.61
     snippetHide
    -0.58
    DeleteBehavior
    -0.58
    migrationBuilder
    -0.58
    smithy
    -0.56
    newswire
    -0.52
    EClass
    -0.50
    POSITIVE LOGITS
     factors
    3.05
     factor
    2.77
     Factors
    2.67
    factors
    2.65
    Factors
    2.53
     FACTORS
    2.41
    factor
    2.39
     factores
    2.38
     Factor
    2.30
    Factor
    2.23
    Activations Density 0.729%

    No Known Activations