© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1459
    Prev
    Next
    INDEX
    Explanations

    symbols, punctuation, and whitespace that indicate formatting elements

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

    mathematical symbols and operations

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

    mathematical and code symbols

    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
     XNUMX
    -0.45
     Accesat
    -0.45
    puri
    -0.44
    原始内容存档于
    -0.44
    Eze
    -0.43
    multicolumn
    -0.43
     Приступљено
    -0.42
     Qaraldi
    -0.41
    Glo
    -0.40
    ?“
    -0.40
    POSITIVE LOGITS
    TintMode
    0.80
     vectorielles
    0.76
     <>",
    0.74
     فريبيس
    0.73
     vettoriale
    0.73
    TagMode
    0.71
     termica
    0.71
     espirituales
    0.70
     $
    0.69
     $\
    0.69
    Activations Density 0.099%

    No Known Activations