© 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. 20-GEMMASCOPE-RES-16K
    11. 193
    Prev
    Next
    INDEX
    Explanations

    references to professional associations and regulatory bodies

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

    preceding types of organizations

    np_acts-logits-general · gemini-2.0-flash

    organizations and bodies

    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
    ViewImports
    -0.78
    AndEndTag
    -0.76
    enterOuterAlt
    -0.63
    OGND
    -0.62
    awtextra
    -0.62
     Audiodateien
    -0.60
     disambiguazione
    -0.60
     surla
    -0.59
    يميديا
    -0.58
    CodedInputStream
    -0.57
    POSITIVE LOGITS
     organizations
    1.33
     organization
    1.33
     organisation
    1.21
     organisations
    1.20
     body
    1.17
     bodies
    1.17
     institutions
    1.06
     Organizations
    1.03
     institution
    1.01
    organizations
    1.01
    Activations Density 0.318%

    No Known Activations