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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1186
    Prev
    Next
    INDEX
    Explanations

    references to collegiate sports achievements and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    championships, tournaments, and divisions

    np_acts-logits-general · gemini-2.0-flash

    championships and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    WebVitals
    -0.58
     дописавши
    -0.54
    </thead>
    -0.53
    Personendaten
    -0.52
    
    -0.50
    Autoritní
    -0.49
    EDEFAULT
    -0.47
    Personensuche
    -0.46
    Diwedd
    -0.44
    IndentedString
    -0.44
    POSITIVE LOGITS
    argate
    0.41
     setempat
    0.40
    boutin
    0.39
    طلاق
    0.39
    auré
    0.39
     bancaire
    0.37
    RTGC
    0.37
    ядок
    0.37
     Cables
    0.37
    orphism
    0.36
    Activations Density 0.218%

    No Known Activations