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. 24-GEMMASCOPE-RES-16K
    6. 13986
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the importance of attention in various contexts

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

    Attention being focused/paid/given

    np_acts-logits-general · gemini-2.0-flash

    attention paid or given

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.59
    مصادر
    -0.57
    SPATH
    -0.57
    prehen
    -0.56
    GEBURTSDATUM
    -0.52
    enger
    -0.52
    juna
    -0.51
    ViewImports
    -0.50
    cornerRadius
    -0.49
     Nasty
    -0.48
    POSITIVE LOGITS
     paid
    0.97
     placed
    0.93
     accorded
    0.89
    paid
    0.81
     given
    0.74
     attaches
    0.72
     Paid
    0.70
     payed
    0.70
     bestowed
    0.68
     devoted
    0.68
    Activations Density 0.369%

    No Known Activations