© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2476
    Prev
    Next
    INDEX
    Explanations

    statements or terms related to assumptions 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 @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elerik
    -0.60
    ergic
    -0.59
    mika
    -0.56
     Waterways
    -0.52
    lammatory
    -0.52
    otides
    -0.51
    vVar
    -0.51
    idian
    -0.51
    argate
    -0.51
     ​​
    -0.50
    POSITIVE LOGITS
     assumed
    1.00
     assume
    0.98
    Assume
    0.97
     Assume
    0.96
    assume
    0.93
     assumption
    0.91
    assumed
    0.88
     assuming
    0.84
     assumes
    0.83
     Assumption
    0.76
    Activations Density 0.245%

    No Known Activations