© 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. 23-GEMMASCOPE-RES-16K
    11. 8884
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or generalizations among items or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zelfde
    -0.54
     eşofman
    -0.53
     arşivlendi
    -0.50
    ⟬
    -0.49
     propOrder
    -0.48
    ripe
    -0.48
    principalColumn
    -0.48
    weightedMode
    -0.48
    ContextHolder
    -0.47
     hırka
    -0.47
    POSITIVE LOGITS
    VersionUID
    0.47
    ChildScrollView
    0.47
     insuffisamment
    0.46
     OFDb
    0.42
     препратки
    0.39
     Gemeinsame
    0.38
     initializer
    0.38
    sidemargin
    0.34
    Cordialement
    0.34
     picker
    0.33
    Activations Density 0.440%

    No Known Activations