© 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. 3-GEMMASCOPE-RES-16K
    11. 5804
    Prev
    Next
    INDEX
    Explanations

    references to artistic or literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istore
    -0.44
    ordion
    -0.38
    uccino
    -0.38
    shid
    -0.37
    throwaway
    -0.37
    chaun
    -0.36
    最快更新
    -0.36
    ToRefresh
    -0.35
    odorant
    -0.35
    versicherung
    -0.35
    POSITIVE LOGITS
     works
    3.78
     Works
    3.55
    Works
    3.30
     WORKS
    3.23
    works
    3.11
    WORKS
    2.80
     obras
    2.13
     Werke
    2.00
     œuvres
    1.90
     Werken
    1.81
    Activations Density 0.071%

    No Known Activations