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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 11974
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters related to HTML or XML entities

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

    HTML entity "&" (ampersand)

    np_acts-logits-general · gemini-2.0-flash

    & followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autoreleasepool
    -0.61
    iencies
    -0.60
    >>>>>>>
    -0.59
     Scotty
    -0.58
    genossen
    -0.56
     BMC
    -0.55
    codegen
    -0.55
    PROP
    -0.55
     Missy
    -0.54
    KeySpec
    -0.51
    POSITIVE LOGITS
     And
    0.80
    And
    0.79
    AND
    0.76
     Andrade
    0.75
     AND
    0.74
    Và
    0.72
    tand
    0.72
     NDL
    0.68
    )&
    0.68
     aand
    0.68
    Activations Density 0.309%

    No Known Activations