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. 12275
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values and patterns in numeric formats

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

    U.S. Supreme Court citations

    np_acts-logits-general · gemini-2.0-flash

    numbers in legal citations

    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
    hnte
    -0.51
     FORCE
    -0.49
    acca
    -0.48
    "}")
    -0.48
    apie
    -0.44
    force
    -0.44
     propOrder
    -0.44
    ysacchar
    -0.43
    BagLayout
    -0.43
    GIUM
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.81
    
    0.67
     viewDidLoad
    0.62
    ContentAsync
    0.60
    rrggbb
    0.60
     Thirdly
    0.60
    posób
    0.60
     ModelExpression
    0.56
    matchCondition
    0.56
     comigo
    0.56
    Activations Density 0.853%

    No Known Activations