© 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. 21-GEMMASCOPE-RES-16K
    11. 12316
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "review" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahomet
    -0.65
    jsonwebtoken
    -0.62
    gemeester
    -0.61
    fjspx
    -0.60
     NSCoder
    -0.60
     flanges
    -0.59
    cahontas
    -0.59
    Personendaten
    -0.59
    patine
    -0.59
    thschild
    -0.59
    POSITIVE LOGITS
     Review
    1.05
     review
    1.03
    review
    1.00
    Review
    0.96
     REVIEW
    0.91
     reviewing
    0.87
     reviewed
    0.81
     reviews
    0.80
    REVIEW
    0.79
     Reviewing
    0.76
    Activations Density 0.104%

    No Known Activations