© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12473
    Prev
    Next
    INDEX
    Explanations

    expressions of completion or finishing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citoy
    -0.56
     vectorielle
    -0.53
     wektor
    -0.47
     vectorielles
    -0.47
     sanguí
    -0.46
    mparas
    -0.44
     genética
    -0.44
     campes
    -0.42
     yyq
    -0.42
     kurtka
    -0.42
    POSITIVE LOGITS
     Finish
    1.39
    finish
    1.38
     finish
    1.37
    Finish
    1.30
     FINISH
    1.27
     finishing
    1.27
    FINISH
    1.27
    finishing
    1.21
     Finishing
    1.21
     Finished
    1.21
    Activations Density 0.114%

    No Known Activations