© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28288
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions involving equations and their results

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

    solve, solutions, prime factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '),
    
    -0.63
    tvguidetime
    -0.59
    )))
    
    -0.53
    '],
    
    -0.52
    )),
    
    -0.50
    '))
    
    -0.50
    )}{\
    -0.50
    '){
    
    -0.49
     فريبيس
    -0.49
    "],
    
    -0.48
    POSITIVE LOGITS
     gills
    0.65
    ؤلاء
    0.61
    Diwedd
    0.61
    abinieri
    0.59
     Validity
    0.59
    Solución
    0.57
    AxisAlignment
    0.57
     nationalities
    0.56
     Reſ
    0.56
     UITextField
    0.56
    Activations Density 0.126%

    No Known Activations