© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11138
    Prev
    Next
    INDEX
    Explanations

    comparisons and conditions related to performance metrics and functionality in technical contexts

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

    Indicates a change, either positive or negative

    np_acts-logits-general · gemini-2.0-flash

    high or low measurements

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ValueStyle
    -0.89
    bootstrapcdn
    -0.70
     transfieras
    -0.68
    ImageContext
    -0.68
    MigrationBuilder
    -0.68
    tagHelperRunner
    -0.66
    mybatisplus
    -0.65
    出版年
    -0.65
     esternos
    -0.64
     jScrollPane
    -0.63
    POSITIVE LOGITS
     high
    1.25
     low
    1.16
     higher
    1.15
     excellent
    1.12
     strong
    1.02
     reduced
    1.00
     increased
    0.96
     exceptional
    0.96
     lower
    0.95
     superior
    0.93
    Activations Density 1.279%

    No Known Activations