© 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. 38-GEMMASCOPE-RES-16K
    11. 7595
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs or formal arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.46
    WithIOException
    -0.41
     lendemain
    -0.39
     vastaan
    -0.39
     Einfluß
    -0.39
    Autoritní
    -0.39
     ujednoznacz
    -0.38
    TintMode
    -0.37
    Amicalement
    -0.37
    liceerd
    -0.36
    POSITIVE LOGITS
     arguments
    0.59
     Lemma
    0.59
    arguments
    0.57
     Arguments
    0.57
    pigeon
    0.56
     lemma
    0.55
    yntaxException
    0.54
    Argument
    0.53
     Argument
    0.52
    Lemma
    0.52
    Activations Density 1.872%

    No Known Activations