© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 229
    Prev
    Next
    INDEX
    Explanations

    references to sinks and drainage systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    near "water," "tap," or "sink."

    np_acts-logits-general · gemini-2.0-flash

    taps and sinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
    Negative Logits
     صوتيه
    -0.50
    ocere
    -0.43
    áře
    -0.43
    nalités
    -0.42
    uxxxx
    -0.40
    Външни
    -0.40
     redefined
    -0.40
     identificação
    -0.40
     onPostExecute
    -0.40
    OCCURRED
    -0.39
    POSITIVE LOGITS
     sink
    0.75
     sinks
    0.68
     Sink
    0.64
    sink
    0.60
    Sink
    0.58
     faucet
    0.56
     faucets
    0.54
     Sinks
    0.51
     taps
    0.50
     tap
    0.47
    Activations Density 0.270%

    No Known Activations