© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 555
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related elements, particularly in the context of emails or message handling

    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
     CreateTagHelper
    -0.69
    CodeDom
    -0.59
    GraphicsUnit
    -0.57
    __(/*!
    -0.56
    DIPSETTING
    -0.55
    erialization
    -0.55
     }}"></
    -0.54
     Lightboxes
    -0.53
    awtextra
    -0.50
    исленность
    -0.48
    POSITIVE LOGITS
     title
    3.30
    title
    2.79
     Title
    2.78
     titles
    2.63
    Title
    2.63
     TITLE
    2.53
     título
    2.40
    TITLE
    2.37
     titel
    2.34
     Titles
    2.17
    Activations Density 0.432%

    No Known Activations