© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1323
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical data or statistics

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

    numerical data and references to research publications

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

    numbers following 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAlignment
    -0.64
    ImageContext
    -0.62
     estatales
    -0.58
     estatal
    -0.56
    UnknownFieldSet
    -0.56
    parametrize
    -0.53
     épis
    -0.52
    новништво
    -0.52
    +#+#
    -0.51
     manières
    -0.51
    POSITIVE LOGITS
    migrationBuilder
    0.63
    cloudfront
    0.62
     HasFactory
    0.59
    WriteTagHelper
    0.59
     AssemblyProduct
    0.58
    )++;
    0.57
    expandindo
    0.57
    InstrumentedTest
    0.54
     cogniz
    0.53
     ded
    0.52
    Activations Density 0.182%

    No Known Activations