© 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. 13-GEMMASCOPE-RES-65K
    6. 57478
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented programming concepts, particularly related to the 'self' keyword in Python

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')),
    -0.68
    liston
    -0.66
    ']],
    -0.65
    ()))
    
    -0.64
    ++];
    -0.63
     '\\;'
    -0.62
    ))$.
    -0.60
    ())),
    -0.60
    ']),
    -0.60
    )),
    
    -0.60
    POSITIVE LOGITS
    MemoryWarning
    0.59
    NonNull
    0.54
    Примечания
    0.51
     transférez
    0.49
    InstanceState
    0.49
    yntaxException
    0.49
    toHaveBeenCalled
    0.49
    forName
    0.48
    Autoritní
    0.47
    complexType
    0.46
    Activations Density 0.003%

    No Known Activations