© 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. 4537
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or praise of work and talent

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

    Adverbs describing positive qualities

    np_acts-logits-general · gemini-2.0-flash

    skillfully done

    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
    Ahoj
    -0.34
    Externé
    -0.33
     liever
    -0.31
     некоторые
    -0.31
    Aiheesta
    -0.31
     myś
    -0.31
    ปก
    -0.31
     ocas
    -0.30
    Famille
    -0.30
    onPressed
    -0.30
    POSITIVE LOGITS
     cleverly
    0.88
     excellently
    0.86
     skillfully
    0.84
     expertly
    0.77
     admirably
    0.76
     habile
    0.75
     nicely
    0.73
     smartly
    0.73
     flawlessly
    0.73
     autorytatywna
    0.73
    Activations Density 0.221%

    No Known Activations