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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6277
    Prev
    Next
    INDEX
    Explanations

    discussions of advertising and revenue models related to digital devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resaid
    -0.52
     vardır
    -0.50
    described
    -0.47
     extrême
    -0.46
    iStock
    -0.46
     décrit
    -0.45
     dangereux
    -0.42
     schilder
    -0.42
    selfie
    -0.42
     description
    -0.42
    POSITIVE LOGITS
     disappointing
    0.80
     rumours
    0.74
     rumoured
    0.74
    ']))
    
    0.73
     rumored
    0.72
     rumors
    0.72
     ivelany
    0.71
     שוליים
    0.70
     releasing
    0.70
     disappointments
    0.69
    Activations Density 0.400%

    No Known Activations