© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15243
    Prev
    Next
    INDEX
    Explanations

    references to names, particularly those that include variations of "Lat," "Nat," and "Rat."

    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
    iya
    -0.50
    ு
    -0.47
    QMetaType
    -0.46
     dezelve
    -0.44
    CascadeType
    -0.43
    ImageContext
    -0.42
    ه
    -0.41
     mów
    -0.40
     StatelessWidget
    -0.40
     cartaz
    -0.40
    POSITIVE LOGITS
    ting
    0.77
    ters
    0.66
    chet
    0.63
    atouille
    0.61
    ched
    0.59
     least
    0.58
    ted
    0.58
    ty
    0.57
    tttt
    0.56
    chets
    0.55
    Activations Density 0.339%

    No Known Activations