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. 20-GEMMASCOPE-RES-131K
    6. 46090
    Prev
    Next
    INDEX
    Explanations

    references to identifiable entities or classifications within scientific or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Rhestr
    -0.42
     Real
    -0.40
     real
    -0.40
     memili
    -0.38
    Realtime
    -0.36
     invading
    -0.36
    Real
    -0.35
    Beijo
    -0.35
     Commissioner
    -0.35
     Recommended
    -0.34
    POSITIVE LOGITS
    +#+
    0.63
     AssemblyCulture
    0.62
    URLException
    0.60
    MessageOf
    0.56
    ########.
    0.56
    الحياه
    0.55
    WebElementEntity
    0.54
    mybatisplus
    0.52
     referrerpolicy
    0.52
    
    0.50
    Activations Density 0.334%

    No Known Activations