© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11917
    Prev
    Next
    INDEX
    Explanations

    backslashes and other escape characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ciro
    -0.53
     Abad
    -0.49
     rati
    -0.49
    est
    -0.49
    躇
    -0.47
     regent
    -0.47
     Lugo
    -0.46
     Migrant
    -0.46
     is
    -0.46
     pert
    -0.45
    POSITIVE LOGITS
     împre
    0.75
    \{\\
    0.69
    ..\..\
    0.67
    <<"\
    0.65
    ("\\
    0.64
     barbati
    0.62
    zondere
    0.61
     "\
    0.61
    (/\
    0.60
     damskie
    0.60
    Activations Density 0.778%

    No Known Activations