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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13876
    Prev
    Next
    INDEX
    Explanations

    references to agreements or contracts in a business context

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

    Real estate, negotiations, and agreements

    np_acts-logits-general · gemini-2.0-flash

    deal or negotiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]++;
    -0.61
    TabStop
    -0.55
     Diri
    -0.53
    apin
    -0.50
    ("")]
    -0.49
    portlet
    -0.49
    емость
    -0.48
    metheus
    -0.48
    migrationBuilder
    -0.47
    baka
    -0.47
    POSITIVE LOGITS
     deal
    2.14
     deals
    1.87
     Deal
    1.80
    deal
    1.77
    Deal
    1.76
     negotiations
    1.65
     negotiated
    1.62
     DEAL
    1.61
     Deals
    1.57
     negotiation
    1.56
    Activations Density 0.341%

    No Known Activations