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. 19-GEMMASCOPE-RES-16K
    6. 11693
    Prev
    Next
    INDEX
    Explanations

    references to specific products or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.71
    RemoveField
    -0.67
    出版年
    -0.61
    \{\\
    -0.60
     onOptions
    -0.57
    MotionEvent
    -0.57
    HideInInspector
    -0.56
     跳转至
    -0.55
    ImageContext
    -0.55
    +#+#
    -0.54
    POSITIVE LOGITS
    商品は
    0.70
    entire
    0.61
     versatile
    0.60
     company
    0.59
    이는
    0.59
     محصول
    0.58
     innovative
    0.57
     versátil
    0.57
     entire
    0.55
    vikle
    0.55
    Activations Density 0.377%

    No Known Activations