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. 14-GEMMASCOPE-RES-16K
    6. 12999
    Prev
    Next
    INDEX
    Explanations

    references to customer service and recall information related to vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.80
    awtextra
    -0.75
    ValueStyle
    -0.65
     للاسماء
    -0.63
     Wartawan
    -0.63
     MotionEvent
    -0.62
     MessageBoxIcon
    -0.59
     CURIAM
    -0.55
     CGRectMake
    -0.54
     חיצוניים
    -0.54
    POSITIVE LOGITS
    بوابة
    0.69
    Παραπομπές
    0.56
     leſs
    0.56
    DoNot
    0.54
    xically
    0.53
    ={`
    0.52
    ųjų
    0.51
    ьа
    0.51
    anderen
    0.50
     interactiva
    0.50
    Activations Density 0.071%

    No Known Activations