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. 9347
    Prev
    Next
    INDEX
    Explanations

    references to audits and regulatory actions related to competition and market practices

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

    Antitrust and competition violations

    np_acts-logits-general · gemini-2.0-flash

    antitrust and competition law

    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
    IntoConstraints
    -0.81
    发表于
    -0.77
    routeProvider
    -0.75
    tvguidetime
    -0.74
    ChildScrollView
    -0.71
     onPostExecute
    -0.70
    примеча
    -0.70
    ValueStyle
    -0.68
    irement
    -0.67
    ніципалі
    -0.66
    POSITIVE LOGITS
     antitrust
    1.16
     competition
    0.96
     Competition
    0.94
     monopoly
    0.92
     competitive
    0.89
    Competition
    0.83
     monopolies
    0.82
     monopol
    0.82
     monopo
    0.79
    competition
    0.79
    Activations Density 0.287%

    No Known Activations