© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3381
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawing conclusions and inferences

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

    forming an opinion

    np_acts-logits-general · gemini-2.0-flash

    drawing conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Itoa
    -0.63
    ]--;
    -0.60
    cetype
    -0.58
    BeginContext
    -0.57
    kloped
    -0.56
    bric
    -0.55
    metra
    -0.55
     tartalomajánló
    -0.54
    IntoConstraints
    -0.54
     valign
    -0.52
    POSITIVE LOGITS
     conclusion
    2.52
     conclusions
    2.33
     conclude
    2.12
    conclusion
    2.12
     Conclusion
    1.99
     concluded
    1.99
     conclu
    1.90
     Conclusions
    1.88
     conclusión
    1.81
     concl
    1.80
    Activations Density 0.656%

    No Known Activations