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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11443
    Prev
    Next
    INDEX
    Explanations

    code-related syntax, particularly the use of backticks in programming languages for defining or encapsulating values and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.79
    •••
    -0.78
    ••••
    -0.74
    //
    
    -0.72
    葩
    -0.71
     đá
    -0.70
    Bounds
    -0.68
    ه
    -0.68
     neb
    -0.68
     },
    
    -0.67
    POSITIVE LOGITS
     `
    2.07
    .`
    1.92
    =`
    1.90
    :`
    1.90
    >`
    1.80
     (`
    1.80
    (`
    1.79
    {`
    1.75
    )`
    1.72
    `
    1.66
    Activations Density 0.060%

    No Known Activations