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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1059
    Prev
    Next
    INDEX
    Explanations

    occurrences of classes and function definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.64
    abestanden
    -0.64
    
    -0.63
    Попис
    -0.62
    ANTLR
    -0.62
    protoimpl
    -0.60
    TagMode
    -0.59
    +#+#
    -0.58
    expandindo
    -0.58
    principalColumn
    -0.57
    POSITIVE LOGITS
    ################
    0.61
     global
    0.58
    """
    0.58
    """
    
    0.56
     del
    0.55
    '):
    
    0.54
    ##
    0.54
     AssemblyTitle
    0.53
    del
    0.53
    #
    0.52
    Activations Density 0.065%

    No Known Activations