© 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. 4453
    Prev
    Next
    INDEX
    Explanations

    mentions of specific authors, institutions, or concepts related to academic research

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

    author names and initials in academic citations and acknowledgments.

    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
    ammans
    -0.51
     kasarigan
    -0.50
     useAppContext
    -0.44
    cheinend
    -0.43
    webElementXpaths
    -0.41
     guste
    -0.40
     फिर
    -0.39
    tichetta
    -0.39
    ViewFeatures
    -0.38
    ötzlich
    -0.38
    POSITIVE LOGITS
     fVar
    0.57
     getF
    0.54
     FetchType
    0.54
     f
    0.53
    foc
    0.53
    FetchType
    0.52
     Fren
    0.52
     F
    0.52
     Fath
    0.52
    ########.
    0.51
    Activations Density 2.651%

    No Known Activations