© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1686
    Prev
    Next
    INDEX
    Explanations

    corrections or modifications pertaining to academic articles or documentation

    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
    tvguidetime
    -0.94
    StoryboardSegue
    -0.87
     AssemblyProduct
    -0.75
    parsedMessage
    -0.74
     typelib
    -0.73
    TintMode
    -0.73
    XmlAccessType
    -0.68
    Brainz
    -0.68
     للاسماء
    -0.67
    ItemBackground
    -0.67
    POSITIVE LOGITS
     paragraph
    1.51
     sentence
    1.37
     lines
    1.30
     paragraphs
    1.26
     line
    1.22
     sentences
    1.16
     Paragraph
    1.07
    paragraph
    1.07
     Lines
    1.04
     lignes
    1.03
    Activations Density 0.951%

    No Known Activations