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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 103378
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to commercial transactions and activities

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

    commercial context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quis
    -0.36
     Diseño
    -0.35
     situation
    -0.34
    keyup
    -0.33
    자
    -0.33
    ัพท์
    -0.33
    validate
    -0.33
    Eliminar
    -0.32
     Valdés
    -0.32
    weh
    -0.31
    POSITIVE LOGITS
    Commercial
    1.82
     commercial
    1.81
     Commercial
    1.77
    commercial
    1.72
     COMMERCIAL
    1.64
     komer
    1.49
     comercial
    1.49
    COMMERCIAL
    1.45
     commercially
    1.45
     Commerci
    1.41
    Activations Density 0.021%

    No Known Activations