© 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. 9-GEMMASCOPE-RES-16K
    11. 6424
    Prev
    Next
    INDEX
    Explanations

    references to various types of bottles and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.43
    Undefined
    -0.43
     Greer
    -0.39
     вста
    -0.39
    citement
    -0.38
     المعيارى
    -0.37
    paw
    -0.37
     Tucker
    -0.36
     Formación
    -0.36
     awakeFromNib
    -0.36
    POSITIVE LOGITS
     bottle
    1.71
     bottles
    1.61
     Bottle
    1.55
    bottle
    1.51
     Bottles
    1.48
    Bottle
    1.47
    bottles
    1.40
     BOTT
    1.34
     botella
    1.28
     bouteille
    1.26
    Activations Density 0.213%

    No Known Activations