© 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. 36-GEMMASCOPE-RES-16K
    11. 8107
    Prev
    Next
    INDEX
    Explanations

    references to various types of paper products and their usage

    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
    transQ
    -0.73
    bootstrapcdn
    -0.71
    makeConstraints
    -0.68
    RenderAtEndOf
    -0.67
     AssemblyCulture
    -0.65
    <unused43>
    -0.65
    <unused79>
    -0.65
    MethodManager
    -0.65
    <unused68>
    -0.65
    [@BOS@]
    -0.65
    POSITIVE LOGITS
     paper
    3.67
    paper
    3.13
     Paper
    3.08
    Paper
    3.02
     PAPER
    2.86
     papers
    2.80
    PAPER
    2.55
     Papers
    2.36
    papers
    2.31
     papel
    2.28
    Activations Density 0.522%

    No Known Activations