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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3363
    Prev
    Next
    INDEX
    Explanations

    product-related terms, specifically in the context of clothing, accessories, and technology

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

    Clothing items

    np_acts-logits-general · gemini-2.0-flash

    garments and equipment

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GOTREF
    -0.42
    >`;
    -0.40
    kwds
    -0.38
     jadx
    -0.35
    RefNanny
    -0.32
    menso
    -0.32
     échou
    -0.31
     limão
    -0.30
    pushFollow
    -0.30
    Autowired
    -0.30
    POSITIVE LOGITS
    ReusableCell
    0.85
     InputDecoration
    0.72
    siery
    0.67
    
    0.65
     ujednoznacz
    0.65
    IBarButtonItem
    0.61
     StatelessWidget
    0.61
     faſt
    0.59
    出版年
    0.58
    tangentMode
    0.58
    Activations Density 0.969%

    No Known Activations