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. 20-GEMMASCOPE-RES-16K
    6. 1653
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and related terminologies

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

    Ohio law or locations

    np_acts-logits-general · gemini-2.0-flash

    Ohio court districts

    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
    rdoba
    -0.58
     Насе
    -0.53
    Carriera
    -0.52
     defaultstate
    -0.51
     Oaxaca
    -0.51
     Chwiliwch
    -0.50
    TypedDataSet
    -0.48
    "}"
    -0.48
     Tenggara
    -0.47
    rália
    -0.46
    POSITIVE LOGITS
     Cleveland
    1.34
    Cleveland
    1.23
     Ohio
    1.16
     Akron
    1.14
    Ohio
    1.07
    VELAND
    1.04
    leveland
    1.00
     OHIO
    0.96
     Youngstown
    0.94
    CLE
    0.86
    Activations Density 0.171%

    No Known Activations