© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "od" and its variations across different contexts

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

    the word "od" (likely a preposition or abbreviation in non-English text).

    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
    CGContext
    -0.37
    complexContent
    -0.34
    Rhestr
    -0.33
     برانيه
    -0.31
    Organisateur
    -0.31
    a
    -0.29
     Contempor
    -0.28
    ۣ
    -0.28
    {}
    -0.27
    ieR
    -0.27
    POSITIVE LOGITS
     <>",
    0.65
    SharedDtor
    0.63
    uvwxyz
    0.57
    puls
    0.56
     oprot
    0.55
    testens
    0.54
    ſelben
    0.52
    Від
    0.52
    ífero
    0.52
     ſehr
    0.52
    Activations Density 0.040%

    No Known Activations