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. 20-GEMMASCOPE-RES-16K
    6. 8946
    Prev
    Next
    INDEX
    Explanations

    sections or instances where dining or restaurant recommendations are discussed

    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
    <eos>
    -0.70
     kezd
    -0.45
    iconque
    -0.45
     szö
    -0.45
    teryx
    -0.43
     Commencez
    -0.43
    ↵↵↵↵
    -0.43
     yoktur
    -0.42
     legjobb
    -0.42
     nemlig
    -0.41
    POSITIVE LOGITS
    </b>
    1.21
    ?}
    1.11
    </h4>
    1.00
    ?
    
    1.00
    %?
    1.00
    ?]
    1.00
    parsedMessage
    0.97
    ?&
    0.92
    </strong>
    0.92
    .)}
    0.91
    Activations Density 0.215%

    No Known Activations