© 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. 678
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols, particularly those used in programming contexts

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

    programming syntax elements and symbols

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

    closing brackets and parentheses

    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
    SequentialGroup
    -0.89
    addCriterion
    -0.88
    ]:
    -0.88
    "):
    -0.86
    )";
    -0.85
    )++;
    -0.84
    "],
    -0.82
    '):
    -0.82
    WriteTagHelper
    -0.82
    ')):
    -0.79
    POSITIVE LOGITS
    ↵
    0.67
     +
    0.51
     if
    0.49
    if
    0.47
     Picchu
    0.46
    et
    0.41
    ans
    0.41
     numerus
    0.40
    glLoadIdentity
    0.40
    ar
    0.39
    Activations Density 0.053%

    No Known Activations