© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8840
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "train" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onPostExecute
    -0.56
    ViewFeatures
    -0.54
    bootstrapcdn
    -0.52
     ब्रेकडाउन
    -0.51
    WidgetItem
    -0.50
    ubourg
    -0.50
    interopRequire
    -0.50
    substantial
    -0.49
     >=",
    -0.48
    tangentMode
    -0.45
    POSITIVE LOGITS
     training
    1.89
     train
    1.84
     Training
    1.72
     Train
    1.71
    Training
    1.66
    train
    1.66
    Train
    1.65
     trained
    1.62
    training
    1.59
     TRAIN
    1.58
    Activations Density 0.194%

    No Known Activations