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

    Neuronpedia

    Jacobian LensNEW
    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. 40-GEMMASCOPE-RES-16K
    11. 5039
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "S" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PageFactory
    -0.50
    holdet
    -0.50
    archiviato
    -0.49
    NewUrlParser
    -0.46
    писок
    -0.44
    原始内容存档于
    -0.44
    CreateModel
    -0.44
    SharedCtor
    -0.42
    DropTable
    -0.42
     IBOutlet
    -0.42
    POSITIVE LOGITS
    tained
    0.45
    exist
    0.43
    here
    0.42
    liced
    0.41
    cion
    0.40
    RegressionTest
    0.40
    tables
    0.38
     conclusão
    0.38
    izable
    0.37
    tably
    0.37
    Activations Density 0.297%

    No Known Activations