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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16113
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    󠁮
    -0.85
    ⎨
    -0.67
    Pautan
    -0.61
    URLException
    -0.59
     }{@
    -0.56
     تضيفلها
    -0.55
    viewDid
    -0.54
    
    -0.53
    tiple
    -0.52
    ConstraintMaker
    -0.52
    POSITIVE LOGITS
    ↵↵
    0.69
    ↵↵↵
    0.54
    ↵
    0.49
    </h3>
    0.42
    ↵↵↵↵↵↵↵
    0.42
    ↵↵↵↵
    0.41
    </blockquote>
    0.40
    <eos>
    0.40
    ↵↵↵↵↵↵
    0.38
     preſent
    0.38
    Activations Density 0.165%

    No Known Activations