© 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. 23-GEMMASCOPE-RES-16K
    6. 9790
    Prev
    Next
    INDEX
    Explanations

    the presence of specific objects or ingredients related to a task or quest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.43
    __':
    
    -0.33
     suitably
    -0.30
    ganu
    -0.30
     an
    -0.29
    __':
    -0.27
     Maior
    -0.27
    AnchorStyles
    -0.27
    prefixer
    -0.27
    ファン
    -0.26
    POSITIVE LOGITS
    webElementXpaths
    0.89
    richTextPanel
    0.88
     transfieras
    0.72
    MessageOf
    0.65
    ंदीखरीदारी
    0.63
    ➌
    0.59
     незавершена
    0.59
     ویکی‌پدی
    0.57
     defaultstate
    0.57
    contentLoaded
    0.55
    Activations Density 0.476%

    No Known Activations