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. 15-GEMMASCOPE-RES-16K
    6. 12941
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific or statistical representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    henge
    -0.62
     Nautilus
    -0.61
     Bauhaus
    -0.61
     Rimini
    -0.60
     Arjuna
    -0.59
    المناصب
    -0.58
     Baal
    -0.58
     nisso
    -0.58
     Himalaya
    -0.58
     Etrus
    -0.57
    POSITIVE LOGITS
     male
    0.78
     males
    0.75
     females
    0.59
    ArgsConstructor
    0.57
     jure
    0.56
    male
    0.55
     Part
    0.54
     upper
    0.54
     eastern
    0.54
     Northern
    0.54
    Activations Density 0.975%

    No Known Activations