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. 25-GEMMASCOPE-RES-16K
    6. 1829
    Prev
    Next
    INDEX
    Explanations

    tax-related terms and concepts associated with legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barnett
    -0.83
     Polak
    -0.75
     Rohit
    -0.69
     Belo
    -0.66
     ROD
    -0.66
     Plin
    -0.65
     Chandra
    -0.65
     Cabrera
    -0.65
     Bayley
    -0.64
     Hewitt
    -0.64
    POSITIVE LOGITS
     SDI
    0.73
     Moffat
    0.71
     Strickland
    0.69
     Dooley
    0.68
     Gea
    0.67
     Beal
    0.65
     Sut
    0.64
     Spe
    0.63
     Luigi
    0.61
    Sut
    0.60
    Activations Density 1.175%

    No Known Activations