© 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. 27-GEMMASCOPE-RES-16K
    6. 10572
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis methods and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.47
    原始内容存档
    -0.40
    ########.
    -0.39
     disponibilités
    -0.38
     Nebel
    -0.37
     Kinders
    -0.34
    тех
    -0.34
    存于互联网档案馆
    -0.33
     tæn
    -0.33
    ડી
    -0.32
    POSITIVE LOGITS
     predictor
    0.69
     regression
    0.68
     predictors
    0.67
     explanatory
    0.66
     predictive
    0.65
    lanatory
    0.61
     Regression
    0.60
    modelBuilder
    0.60
     variables
    0.59
    Predict
    0.59
    Activations Density 2.073%

    No Known Activations