© 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. 12-GEMMASCOPE-RES-16K
    11. 3348
    Prev
    Next
    INDEX
    Explanations

    sentences related to wish lists and requests for items or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     publicación
    -0.42
     onBind
    -0.39
     vedno
    -0.36
     publicação
    -0.35
     dziennik
    -0.35
     Heraus
    -0.35
     jornalista
    -0.33
     hoort
    -0.33
     mystère
    -0.32
     Italij
    -0.32
    POSITIVE LOGITS
     demand
    0.79
     Demand
    0.77
    demand
    0.77
     request
    0.76
    Demand
    0.72
     wishlist
    0.70
     requesting
    0.69
     demands
    0.69
     Demands
    0.68
     requests
    0.68
    Activations Density 0.837%

    No Known Activations