© 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. 601
    Prev
    Next
    INDEX
    Explanations

    tokens that indicate the start of new sections or paragraphs

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

    the presence of boilerplate text or document structure markers

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

    archaic or Spanish words

    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
    ":
    -0.63
     (
    -0.62
     I
    -0.62
     a
    -0.61
     AssemblyTitle
    -0.61
    -',
    -0.60
    ':
    -0.59
    brainly
    -0.55
     
    -0.55
    *',
    -0.54
    POSITIVE LOGITS
     Jefus
    1.14
     whoſe
    1.13
     Reſ
    1.09
     itſelf
    1.09
     Houſe
    1.09
     Theſe
    1.04
     Diſ
    1.02
     myſelf
    1.02
    ſelf
    1.01
     houſe
    1.01
    Activations Density 0.117%

    No Known Activations