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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 14630
    Prev
    Next
    INDEX
    Explanations

    character names and terms in various languages, particularly those with diacritics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.75
    <strong>
    -0.65
    ule
    -0.62
     похо
    -0.61
    almaz
    -0.61
    5
    -0.60
    <h2>
    -0.60
    oid
    -0.60
     access
    -0.59
    もら
    -0.59
    POSITIVE LOGITS
     Beyoncé
    0.88
     Erdoğan
    0.86
     Citroën
    0.85
    Rüyada
    0.85
     Bogotá
    0.84
     Nestlé
    0.84
     doughnuts
    0.84
    
    0.82
     Condé
    0.82
    hitheatre
    0.81
    Activations Density 0.479%

    No Known Activations