Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3330
    Prev
    Next
    INDEX
    Explanations

    statements related to financial forecasts and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.41
    messageInfo
    -0.41
     Савезне
    -0.39
     ComVisible
    -0.37
     maternidade
    -0.37
     seduta
    -0.36
    ValueStyle
    -0.36
    GoogleMap
    -0.36
     beden
    -0.36
     BIBSYS
    -0.35
    POSITIVE LOGITS
     prediction
    1.16
     predictions
    1.09
     forecast
    0.98
     forecasts
    0.95
    Prediction
    0.93
     Prediction
    0.93
    prediction
    0.92
     predict
    0.90
     predicting
    0.89
    预测
    0.88
    Activations Density 0.399%

    No Known Activations