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. 20-GEMMASCOPE-RES-16K
    6. 9855
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific measurements and their uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AlterField
    -0.63
     ujednoznacz
    -0.62
    ceptre
    -0.61
     resourceCulture
    -0.60
     للمعارف
    -0.60
    期刊论文
    -0.59
     virgins
    -0.58
     colourless
    -0.57
    ovascular
    -0.57
     Jefus
    -0.57
    POSITIVE LOGITS
     effects
    0.84
     inherent
    0.83
     variation
    0.76
     differences
    0.76
     variability
    0.75
     variations
    0.75
     factors
    0.73
     effets
    0.72
     noise
    0.72
     intrinsic
    0.70
    Activations Density 2.133%

    No Known Activations