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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6498
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and citation information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic citation and reference formatting patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considérons
    -0.48
    wicz
    -0.46
    朋
    -0.43
     altrett
    -0.43
     engagé
    -0.43
    umsi
    -0.43
    alakip
    -0.43
    lorin
    -0.41
     talleres
    -0.41
    (!__
    -0.41
    POSITIVE LOGITS
     pp
    0.71
     للاسماء
    0.51
    nofollow
    0.46
    andExpect
    0.45
    Попис
    0.41
     surla
    0.39
     ppl
    0.39
    WebServlet
    0.37
    InvalidProtocol
    0.37
     pages
    0.36
    Activations Density 0.438%

    No Known Activations