© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2027
    Prev
    Next
    INDEX
    Explanations

    references to errors, corrections, and appeals in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Misspellings, typos, and corrections

    np_acts-logits-general · gemini-2.0-flash

    highlighting errors and corrections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Agnew
    -0.30
     tand
    -0.27
     Situationen
    -0.27
     обу
    -0.26
    брь
    -0.26
     situations
    -0.26
     우
    -0.25
     meet
    -0.25
     eben
    -0.24
    Situ
    -0.24
    POSITIVE LOGITS
     incorrect
    1.22
     Incorrect
    1.09
     incorrectly
    1.09
    incorrect
    1.07
     wrong
    1.05
     misspelled
    1.03
     erroneous
    1.02
    wrong
    1.02
     Wrong
    1.02
    Wrong
    0.96
    Activations Density 0.639%

    No Known Activations