© 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-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8264
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, especially related to voting, claims, legal terminology, and sports statistics

    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
     Treiber
    -0.45
    Beskrivelse
    -0.45
    Preference
    -0.44
    存于互联网档案馆
    -0.43
    transQ
    -0.43
    mybatisplus
    -0.41
     Apertura
    -0.41
    PRIORITY
    -0.40
    webElementXpaths
    -0.39
     상세
    -0.39
    POSITIVE LOGITS
     because
    0.88
     puisque
    0.85
     puisqu
    0.82
     porque
    0.76
     ponieważ
    0.75
     thanks
    0.73
     omdat
    0.73
    because
    0.69
     благодаря
    0.68
     deoarece
    0.68
    Activations Density 0.687%

    No Known Activations