© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7510
    Prev
    Next
    INDEX
    Explanations

    references to the business sector and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.72
     CreateTagHelper
    -0.62
    ftagPool
    -0.62
     betweenstory
    -0.60
    rrggbb
    -0.59
     مرئيه
    -0.56
     Signalez
    -0.55
    Hentet
    -0.54
     فريبيس
    -0.54
     ModelExpression
    -0.53
    POSITIVE LOGITS
    Business
    0.80
     Business
    0.63
    business
    0.55
     Bewußt
    0.46
     Geschäfts
    0.46
    zugehen
    0.45
     blessed
    0.44
     guste
    0.44
     valmis
    0.44
     gesloten
    0.43
    Activations Density 0.375%

    No Known Activations