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. 5162
    Prev
    Next
    INDEX
    Explanations

    dialogue markers and phrases indicating speech in text

    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
     critics
    -0.53
    bloomberg
    -0.51
    Contexto
    -0.48
    pyplot
    -0.48
     investors
    -0.47
    #![
    -0.47
    poro
    -0.46
     T
    -0.45
    preventDefault
    -0.45
     analysts
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.86
     StatefulWidget
    0.71
    ]--;
    0.70
    DockStyle
    0.69
    Personensuche
    0.69
     tartalomajánló
    0.65
     Италијани
    0.65
     kasarigan
    0.65
    onActivityResult
    0.62
    parsedMessage
    0.59
    Activations Density 0.096%

    No Known Activations