© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7183
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'or' and other terms indicating options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.58
     contrário
    -0.54
    Autoritní
    -0.54
    Hentet
    -0.52
    ectady
    -0.51
     HasFactory
    -0.50
    tagHelperRunner
    -0.48
    principalTable
    -0.48
    出版年
    -0.48
     AttributeSet
    -0.48
    POSITIVE LOGITS
     possibly
    0.65
     preferably
    0.64
     sometimes
    0.64
     fewer
    0.63
     maybe
    0.60
     occasionally
    0.59
     ideally
    0.58
     voire
    0.56
     thậm
    0.54
    possibly
    0.53
    Activations Density 0.385%

    No Known Activations