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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68469
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and activities

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

    business activities and company operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    évaluateur
    -0.46
    canestro
    -0.40
    rehension
    -0.39
     ripped
    -0.39
     chunk
    -0.39
    kkue
    -0.39
     abord
    -0.38
     Besøkt
    -0.38
    beutel
    -0.37
     חיצוניים
    -0.37
    POSITIVE LOGITS
    OGND
    0.72
     verksamhet
    0.68
     activities
    0.67
     industry
    0.66
     industries
    0.65
     verksam
    0.64
     operations
    0.63
    industry
    0.63
     Industry
    0.63
    Industry
    0.63
    Activations Density 0.024%

    No Known Activations