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. 65620
    Prev
    Next
    INDEX
    Explanations

    elements related to e-commerce functionalities and transactions

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

    purchase history or account details

    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
    PullParser
    -0.37
     PROFESSIONAL
    -0.36
     públicas
    -0.35
     ROLL
    -0.35
    IBOutlet
    -0.34
    formKey
    -0.34
     Forschung
    -0.33
     RESEARCH
    -0.33
     RISK
    -0.33
     Öffentlich
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.62
     estekak
    0.58
     AssemblyCulture
    0.58
     تضيفلها
    0.55
    ISODE
    0.52
     متعلقه
    0.51
     Савезне
    0.50
     BorderSide
    0.50
     saites
    0.47
    Спољашње
    0.46
    Activations Density 0.001%

    No Known Activations