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. 9982
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and its variations in text

    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
     abbandon
    -0.68
    <bos>
    -0.68
     alimentazione
    -0.66
     aumentare
    -0.62
     argint
    -0.61
     autorité
    -0.61
     Assyrian
    -0.59
     attravers
    -0.59
     affrontare
    -0.59
     occasione
    -0.59
    POSITIVE LOGITS
     few
    1.28
     lot
    1.03
     couple
    0.96
     different
    0.95
     very
    0.93
     pair
    0.92
     large
    0.92
     handful
    0.92
     number
    0.91
    "):
    
    0.91
    Activations Density 1.228%

    No Known Activations