© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    discussions and measurements related to accuracy and precision in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')}}
    -0.34
     bul
    -0.31
     Sola
    -0.30
    "");
    -0.30
    越大
    -0.30
     aj
    -0.30
     Ler
    -0.30
    Sola
    -0.29
    ModelAttribute
    -0.29
     stock
    -0.28
    POSITIVE LOGITS
     accuracy
    1.31
     precision
    1.20
     Accuracy
    1.08
     precisión
    1.06
    精度
    1.05
    accuracy
    1.05
    precision
    1.03
     précision
    1.02
     ACCUR
    0.99
    Accuracy
    0.98
    Activations Density 1.235%

    No Known Activations