© 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. 15543
    Prev
    Next
    INDEX
    Explanations

    certainty and persistence in opinions or conditions despite challenges

    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
    httphttps
    -0.51
    PerformLayout
    -0.42
    Jereo
    -0.42
     ***!
    -0.39
    ordning
    -0.39
    Nuorodos
    -0.38
     Bersama
    -0.38
    chieht
    -0.37
    AndEndTag
    -0.37
     للاسماء
    -0.37
    POSITIVE LOGITS
     ändå
    0.79
     trotzdem
    0.79
     still
    0.77
     nonetheless
    0.75
     nevertheless
    0.73
    Still
    0.70
     dennoch
    0.70
    still
    0.69
     ftill
    0.68
     ſtill
    0.68
    Activations Density 0.297%

    No Known Activations