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. 4-GEMMASCOPE-RES-16K
    6. 3371
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and control characters commonly used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uParam
    -0.95
     "..\..\
    -0.88
    ::_('
    -0.85
    /***/
    -0.84
     EIS
    -0.82
    guenos
    -0.80
    ViewChild
    -0.79
     Jolie
    -0.78
    ktör
    -0.78
    endpush
    -0.77
    POSITIVE LOGITS
    ,
    
    0.91
     Fras
    0.75
     =
    
    0.75
     {},
    
    0.74
     HAST
    0.74
     阅读
    0.71
    becken
    0.71
     +
    
    0.71
     plac
    0.69
     Pfund
    0.69
    Activations Density 0.319%

    No Known Activations