© 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. 532
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming constructs

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

    HTML and Java-related syntax elements, focusing on attributes and comments in code

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

    collect terms in algebraic expressions

    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
    -0.76
    الحياه
    -0.58
     CURIAM
    -0.56
    chik
    -0.54
    WithEmail
    -0.54
    zzleHttp
    -0.53
    Клуб
    -0.52
    twimg
    -0.52
    PYX
    -0.51
     onCancelled
    -0.51
    POSITIVE LOGITS
     hearts
    0.58
     nakalista
    0.57
    Viited
    0.52
    Atsauces
    0.51
     Efq
    0.50
     poffe
    0.50
     cauſe
    0.49
     PTE
    0.48
     ſtate
    0.47
     BZ
    0.47
    Activations Density 0.083%

    No Known Activations