© 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. 23-GEMMASCOPE-RES-16K
    11. 8823
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'a' in a textual context, indicating an emphasis on specific properties or variables

    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
    queles
    -0.69
     Numerade
    -0.68
     Grüsse
    -0.63
     miniaturka
    -0.63
     wzglę
    -0.63
     voľ
    -0.63
     ilustracja
    -0.60
     możli
    -0.59
     iſt
    -0.59
     eléct
    -0.58
    POSITIVE LOGITS
    A
    0.96
     a
    0.94
     A
    0.93
    getA
    0.86
    a
    0.79
    aA
    0.66
    rA
    0.63
    OA
    0.62
     b
    0.60
    fA
    0.60
    Activations Density 0.509%

    No Known Activations