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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5715
    Prev
    Next
    INDEX
    Explanations

    structural or formatting cues in programming or logical sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mérimée
    -0.55
    esgue
    -0.55
    henswürdigkeiten
    -0.53
    BorderSize
    -0.51
     Faso
    -0.49
    */}
    -0.49
     betweenstory
    -0.49
     للمعارف
    -0.48
     gynnwys
    -0.48
    ochet
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.74
    Geplaatst
    0.73
    <bos>
    0.69
    ########.
    0.65
    webElementXpaths
    0.63
     referenties
    0.59
    Билгалдахарш
    0.57
     незавершена
    0.54
    Gambas
    0.54
     étend
    0.53
    Activations Density 0.992%

    No Known Activations