© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15297
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically those at the end of statements or items in lists

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

    Code snippets or programming-related syntax

    np_acts-logits-general · gemini-2.0-flash

    closing brace or bracket

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     chi̍t
    -0.54
    Portály
    -0.52
     Barnet
    -0.47
     pł
    -0.47
    stuhl
    -0.47
    Externí
    -0.47
     val
    -0.47
    AutoScaleMode
    -0.47
     res
    -0.46
    filo
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.76
     Roskov
    0.76
    writeFieldEnd
    0.67
    DoubleQuotes
    0.66
     للاسماء
    0.63
    \{\\
    0.59
    "]),
    0.58
    ，“
    0.57
    AddTagHelper
    0.56
     مشين
    0.55
    Activations Density 0.150%

    No Known Activations