© 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. 33-GEMMASCOPE-RES-16K
    11. 7892
    Prev
    Next
    INDEX
    Explanations

    elements related to coding, programming errors, and software licensing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bol
    -0.58
     bol
    -0.57
     Ari
    -0.56
    fare
    -0.56
    <eos>
    -0.54
    ese
    -0.54
     Stre
    -0.53
     Ber
    -0.53
     Bol
    -0.53
     Tal
    -0.52
    POSITIVE LOGITS
     tartalomajánló
    0.77
    rungsseite
    0.73
     miniaturka
    0.71
    parsedMessage
    0.69
     desmotivaciones
    0.68
     betweenstory
    0.68
    berdayakan
    0.66
     sprüche
    0.66
    uxxxx
    0.64
     contextLoads
    0.64
    Activations Density 1.611%

    No Known Activations