© 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. 7-GEMMASCOPE-RES-16K
    11. 14287
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "describe" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsonwebtoken
    -0.57
    principalColumn
    -0.57
    ########.
    -0.56
    transQ
    -0.52
    yntaxException
    -0.51
     Bally
    -0.49
     rooster
    -0.49
     Mullen
    -0.48
    waitKey
    -0.48
    Населення
    -0.48
    POSITIVE LOGITS
     describe
    2.06
     description
    1.92
     Describe
    1.90
     describing
    1.90
     describes
    1.90
     described
    1.84
     DESCR
    1.84
    describe
    1.79
    Describe
    1.74
     décrire
    1.73
    Activations Density 0.171%

    No Known Activations