© 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. 1394
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

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

    mathematical notation and symbols

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

    symbols, subscripts

    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
     }}=\
    -0.64
     $=
    -0.62
     }=
    -0.61
     }=\
    -0.60
     }}}{
    -0.58
     <-
    -0.57
     }}=
    -0.54
     =
    -0.54
    =
    -0.54
    =");
    -0.54
    POSITIVE LOGITS
     الحره
    0.90
     للمعارف
    0.84
    UnsafeEnabled
    0.80
     فريبيس
    0.80
    rungsseite
    0.78
    \{\\
    0.76
    
    0.75
    MessageOf
    0.75
    省市镇
    0.75
    vician
    0.74
    Activations Density 0.510%

    No Known Activations