© 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. 33-GEMMASCOPE-RES-16K
    11. 13006
    Prev
    Next
    INDEX
    Explanations

    references to plumbing and home repairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⟬
    -0.57
    Personendaten
    -0.57
     Administrativna
    -0.57
     CreateTagHelper
    -0.56
     AssemblyCulture
    -0.54
     صوتيه
    -0.53
     typelib
    -0.52
     HFILL
    -0.50
    #+#
    -0.49
    ➟
    -0.48
    POSITIVE LOGITS
     sink
    1.14
     sinks
    1.05
    sink
    0.90
     Sink
    0.90
     bathtub
    0.87
     toilet
    0.85
     faucets
    0.82
     Sinks
    0.81
     faucet
    0.81
    Sink
    0.80
    Activations Density 0.112%

    No Known Activations