© 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. 20-GEMMASCOPE-RES-16K
    11. 7278
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal violations and probation conditions

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

    doubt or uncertainty

    np_acts-logits-general · gemini-2.0-flash

    allegedly, supposed, purported

    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
    eraard
    -0.62
     compréhen
    -0.57
     adaptarse
    -0.54
     bisog
    -0.53
    hopefully
    -0.53
    ัจ
    -0.52
    raszamy
    -0.51
    nextProps
    -0.51
     aandacht
    -0.51
     everybody
    -0.50
    POSITIVE LOGITS
     allegedly
    1.50
     alleged
    1.28
     supuestamente
    1.17
     purported
    1.12
     supposedly
    1.03
     improperly
    0.95
     supposed
    0.95
    supposed
    0.95
    alleg
    0.94
     कथ
    0.92
    Activations Density 1.293%

    No Known Activations