© 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. 22-GEMMASCOPE-RES-16K
    6. 14520
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANTE
    -0.35
    ensch
    -0.32
    MemoryWarning
    -0.32
    AnchorTagHelper
    -0.32
     endorse
    -0.31
     ev
    -0.31
     casse
    -0.31
     Anth
    -0.30
     Klar
    -0.30
    mayr
    -0.29
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    новништво
    0.62
    :✨
    0.58
    principalColumn
    0.57
    ToBounds
    0.57
    aarrggbb
    0.56
    ModelSerializer
    0.55
     Wiktionnaire
    0.55
    Espèce
    0.54
    CloseOperation
    0.54
    Activations Density 1.085%

    No Known Activations