© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16067
    Prev
    Next
    INDEX
    Explanations

    HTML and XML tags or elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.44
     étoient
    -0.44
    //
    -0.44
    ništ
    -0.43
    httphttps
    -0.43
    TypedDataSet
    -0.42
    forRoot
    -0.40
     surla
    -0.40
    :✨
    -0.40
    脚注の使い方
    -0.39
    POSITIVE LOGITS
     span
    2.16
    span
    1.97
    Span
    1.48
     Span
    1.48
     SPAN
    1.27
    SPAN
    1.16
     spans
    1.09
    espan
    0.97
     spanning
    0.96
     spanned
    0.96
    Activations Density 0.206%

    No Known Activations