© 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. 39-GEMMASCOPE-RES-16K
    11. 2775
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas and colons, in structured data or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.43
     settore
    -0.42
     memasak
    -0.41
     policiales
    -0.40
     Meksika
    -0.40
    jší
    -0.40
     Einfluß
    -0.40
     juges
    -0.39
    CppMethod
    -0.39
     asmen
    -0.38
    POSITIVE LOGITS
    WriteTagHelper
    0.65
    ",
    0.63
     snippetHide
    0.61
    "
    0.54
    [
    0.53
    \
    0.53
    IsContent
    0.52
    0.52
     //$
    0.52
     resourceCulture
    0.49
    Activations Density 0.250%
    No Known Activations