© 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. 8436
    Prev
    Next
    INDEX
    Explanations

    elements related to experiments or studies, including variables and results reporting

    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
    bootstrapcdn
    -0.47
     Autorisations
    -0.43
    FontOfSize
    -0.42
     Paglinawan
    -0.40
     الحره
    -0.39
    awakeFromNib
    -0.39
    SupportActionBar
    -0.39
    Biographie
    -0.39
    gento
    -0.37
     ComVisible
    -0.37
    POSITIVE LOGITS
     results
    0.52
    results
    0.49
    writeFieldEnd
    0.48
    出版年
    0.47
     onPostExecute
    0.45
     finalize
    0.44
     final
    0.44
    Results
    0.43
    resultados
    0.42
     kết
    0.42
    Activations Density 0.411%

    No Known Activations