© 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. 22-GEMMASCOPE-RES-16K
    11. 14774
    Prev
    Next
    INDEX
    Explanations

    words related to assumptions and hypotheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.56
    ergic
    -0.54
     ​​
    -0.50
    mika
    -0.49
    idian
    -0.47
    SocketAddress
    -0.47
     Mitar
    -0.46
    perity
    -0.46
    ody
    -0.46
    argate
    -0.45
    POSITIVE LOGITS
     assume
    1.09
     assumed
    1.08
    Assume
    1.06
     Assume
    1.05
    assume
    1.03
     assumption
    1.00
    assumed
    0.97
     assuming
    0.92
     assumes
    0.90
     assumptions
    0.85
    Activations Density 0.283%

    No Known Activations