© 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. 1384
    Prev
    Next
    INDEX
    Explanations

    specific placeholders or markers indicating the start of sections or transitions in text

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

    instances of the beginning of a section or chapter in a document

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

    date and time formats

    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
    expandindo
    -0.88
    LookAnd
    -0.82
    DockStyle
    -0.82
    脚注の使い方
    -0.82
     resourceCulture
    -0.72
    OGND
    -0.72
    HtmlAttribute
    -0.71
    TagMode
    -0.66
    TintMode
    -0.65
     mxArray
    -0.65
    POSITIVE LOGITS
    र्ण
    0.48
    werd
    0.47
    RESET
    0.46
     fac
    0.45
    loir
    0.45
    ikom
    0.45
     setDate
    0.44
    JsonNode
    0.44
    gdala
    0.43
     (:
    0.43
    Activations Density 0.063%

    No Known Activations