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. 13-GEMMASCOPE-RES-16K
    6. 282
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics and quantities related to time, participation, and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quantities, fractions, or percentages.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    CDCl
    -0.74
    /**
    -0.56
    tvguidetime
    -0.56
    ElementAt
    -0.55
    IBAction
    -0.54
     indef
    -0.54
     ujednoznacz
    -0.54
    ilies
    -0.54
     SqlDbType
    -0.53
     deleteById
    -0.53
    POSITIVE LOGITS
    SourceChecksum
    0.72
     gering
    0.64
     fewer
    0.60
     Fewer
    0.58
     wenige
    0.56
     less
    0.55
     Reduced
    0.55
     Few
    0.55
     (<
    0.54
     Less
    0.54
    Activations Density 0.376%

    No Known Activations