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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4162
    Prev
    Next
    INDEX
    Explanations

    predictions and estimates related to economic or financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hrung
    -0.52
     Takahashi
    -0.47
     AssemblyTitle
    -0.46
    <%@
    -0.45
    atuan
    -0.45
    icznego
    -0.45
    ="../../
    -0.45
    lernen
    -0.45
    phora
    -0.45
    ASHI
    -0.44
    POSITIVE LOGITS
     prediction
    1.14
     predictions
    1.14
    Prediction
    1.10
     Predictions
    1.10
     predicts
    1.06
     predicting
    1.06
     Prediction
    1.05
     predict
    1.03
    Predictions
    1.01
     predicted
    1.01
    Activations Density 0.421%

    No Known Activations