© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific formatting used in code or technical settings

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

    punctuation marks and symbols representing actions or queries

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

    issue closing or fix

    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
     autorytatywna
    -0.69
    deviantart
    -0.61
    pette
    -0.60
    wpi
    -0.57
     AttributeSet
    -0.53
     JSTOR
    -0.53
     szóci
    -0.52
    MenuView
    -0.52
    τσ
    -0.52
    UserScript
    -0.51
    POSITIVE LOGITS
    Closing
    0.72
     Closing
    0.72
     closing
    0.63
    Fixed
    0.58
     Would
    0.58
     Looks
    0.57
     closed
    0.57
     would
    0.55
     fixed
    0.55
     Fixed
    0.55
    Activations Density 0.108%

    No Known Activations