© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4697
    Prev
    Next
    INDEX
    Explanations

    connections and interactions between various entities and systems, particularly in collaborative and cross-border contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rédients
    -0.39
    ⟬
    -0.37
    낙
    -0.35
    /**
    -0.34
    요
    -0.34
    entrion
    -0.34
    PDOException
    -0.34
     favorite
    -0.34
     Nava
    -0.33
     SOD
    -0.33
    POSITIVE LOGITS
     cross
    0.63
    цездатний
    0.63
    cross
    0.55
    Cross
    0.55
     Cross
    0.55
     kasarigan
    0.54
     crossover
    0.53
     saites
    0.53
     Brücke
    0.53
     CROSS
    0.53
    Activations Density 1.076%

    No Known Activations