Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15291
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section

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

    Code snippets and certain punctuation (, ; ])

    np_acts-logits-general · gemini-2.0-flash

    Q: As The Amino Pap Immun five

    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
     itſelf
    -0.78
     Houſe
    -0.72
     myſelf
    -0.71
     themſelves
    -0.68
     Himself
    -0.68
     himſelf
    -0.64
    parsedMessage
    -0.63
     Monfieur
    -0.62
     iſt
    -0.61
    ⎓
    -0.61
    POSITIVE LOGITS
     and
    0.83
     but
    0.80
     so
    0.71
     which
    0.70
     because
    0.65
     And
    0.64
     even
    0.63
    And
    0.59
    InputBorder
    0.57
     just
    0.56
    Activations Density 0.044%

    No Known Activations