© 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. 22-GEMMASCOPE-RES-16K
    11. 8664
    Prev
    Next
    INDEX
    Explanations

    structured elements within programming or documentation format

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

    preceding references or citations

    np_acts-logits-general · gemini-2.0-flash

    knows that

    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
    ,
    -0.81
     
    -0.70
    .
    -0.70
    :
    -0.69
    -
    -0.68
    (
    -0.62
    a
    -0.61
    /
    -0.60
     (
    -0.60
     a
    -0.59
    POSITIVE LOGITS
     bezeichneter
    1.51
    expandindo
    1.36
    ValueStyle
    1.32
    脚注の使い方
    1.31
     дописавши
    1.29
     مشين
    1.26
     disambiguazione
    1.26
     snippetHide
    1.24
     ostavi
    1.24
     itſelf
    1.23
    Activations Density 0.186%

    No Known Activations