© 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. 568
    Prev
    Next
    INDEX
    Explanations

    the start of new sections or topics in a document

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

    the beginning of text or paragraphs

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

    references, comments, and discussion

    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
    OGND
    -0.53
    XmlAccessType
    -0.52
     endforeach
    -0.52
    webElementGuid
    -0.50
     endwhile
    -0.50
    seteq
    -0.48
    ValueStyle
    -0.47
     *>(
    -0.46
     numberOfRows
    -0.45
    AddTagHelper
    -0.45
    POSITIVE LOGITS
    now
    0.62
    makeConstraints
    0.62
    Intial
    0.62
    createObject
    0.60
     Theſe
    0.58
    initialize
    0.58
     Jefus
    0.57
    OrCreate
    0.56
    synchronized
    0.56
     now
    0.56
    Activations Density 0.025%

    No Known Activations