Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 382
    Prev
    Next
    INDEX
    Explanations

    references to events, especially races and sports-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.54
    rungsseite
    -0.53
    expandindo
    -0.46
    点此举报
    -0.45
    TypedDataSet
    -0.43
    tvguidetime
    -0.43
    FunctionFlags
    -0.42
    __':
    
    -0.42
    ########.
    -0.42
    __":
    
    -0.41
    POSITIVE LOGITS
     racing
    0.44
     raced
    0.43
    arrivo
    0.40
     veterinarians
    0.39
     gallo
    0.39
     étoient
    0.39
    itinéraire
    0.39
     Zähne
    0.38
     shoe
    0.38
     horses
    0.38
    Activations Density 0.025%

    No Known Activations