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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13609
    Prev
    Next
    INDEX
    Explanations

    terms related to forecasts and predictions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements about the future

    np_acts-logits-general · gemini-2.0-flash

    predictions and forecasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    occasione
    -0.40
     تعدى
    -0.38
     mű
    -0.34
    adesivo
    -0.34
     thanking
    -0.32
     Administrativna
    -0.31
     partecipazione
    -0.31
     Beschwerden
    -0.31
     térmico
    -0.30
    alimentation
    -0.28
    POSITIVE LOGITS
     predictions
    2.66
     prediction
    2.64
     predict
    2.44
     predicted
    2.42
     predicting
    2.38
     Predictions
    2.31
     predicts
    2.31
     Prediction
    2.28
    Prediction
    2.17
     forecast
    2.14
    Activations Density 0.859%

    No Known Activations