Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15096
    Prev
    Next
    INDEX
    Explanations

    activities and states related to personal responsibilities and tasks

    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
    存于互联网档案馆
    -0.52
    httphttps
    -0.50
     архивлан
    -0.50
     ब्रेकडाउन
    -0.49
    waitKey
    -0.49
    providedIn
    -0.49
    AppMethodBeat
    -0.48
    lccn
    -0.47
    קיש
    -0.45
     createState
    -0.45
    POSITIVE LOGITS
    忙
    0.67
     busy
    0.66
     sibuk
    0.60
    busy
    0.59
    優先
    0.57
    Busy
    0.56
     duties
    0.55
     preoccupied
    0.54
     Busy
    0.54
     ocupado
    0.52
    Activations Density 0.327%

    No Known Activations