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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10178
    Prev
    Next
    INDEX
    Explanations

    numeric values or variables in a programming context

    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
    Chham
    -0.80
    abestanden
    -0.78
     clearColor
    -0.72
    zee
    -0.68
     Dodo
    -0.67
     ASR
    -0.67
     incomplète
    -0.66
    loro
    -0.65
     transférez
    -0.65
    FieldBuilder
    -0.64
    POSITIVE LOGITS
     val
    2.13
     Val
    2.02
    Val
    1.89
    val
    1.88
     VAL
    1.87
    VAL
    1.81
     Valdez
    1.33
     valet
    1.29
     vals
    1.25
     Valdés
    1.18
    Activations Density 0.028%

    No Known Activations