© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    information related to curfews and their impact on communities

    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
     idag
    -0.54
     पहु
    -0.54
    ियाँ
    -0.53
     wußte
    -0.48
     nôtre
    -0.48
     veramente
    -0.46
    Whilst
    -0.46
     Vám
    -0.45
     Ministre
    -0.45
     Bapak
    -0.45
    POSITIVE LOGITS
     
    0.54
     practised
    0.54
     unauthorised
    0.54
     criticised
    0.53
    ,’’
    0.53
    됐
    0.51
     staffers
    0.50
     unveiled
    0.50
     practising
    0.49
     
    0.49
    Activations Density 0.265%

    No Known Activations