© 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. 22-GEMMASCOPE-RES-16K
    11. 7954
    Prev
    Next
    INDEX
    Explanations

    words conveying positivity or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilha
    -0.54
     Wraith
    -0.54
    Ashlee
    -0.52
     VIAF
    -0.47
     transfer
    -0.46
     cadeia
    -0.46
     trasfer
    -0.45
     Isla
    -0.44
     montanha
    -0.44
     TRANSFER
    -0.44
    POSITIVE LOGITS
    Good
    1.20
     Good
    1.17
     GOOD
    1.12
    good
    1.09
    GOOD
    1.06
     good
    1.05
     Goodwin
    0.82
     Goodman
    0.81
     gud
    0.80
     Хоро
    0.79
    Activations Density 0.069%

    No Known Activations