© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 468
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and predictions

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

    errors, deviations, or discrepancies

    np_acts-logits-general · gemini-2.0-flash

    deviate from expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     sula
    -0.61
     silence
    -0.52
     negligible
    -0.51
     manageable
    -0.51
    igual
    -0.50
    bzero
    -0.49
     replaceable
    -0.48
    Zero
    -0.48
     similares
    -0.48
     silêncio
    -0.48
    POSITIVE LOGITS
     devi
    1.23
     deviate
    1.16
     wrong
    1.12
     incorrect
    1.10
     incorrectly
    1.10
     mis
    1.09
     distorted
    1.02
     mismatch
    1.02
    incorrect
    1.00
     abnormal
    1.00
    Activations Density 0.751%

    No Known Activations