© 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 EvalsExportsAPI 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. 4350
    Prev
    Next
    INDEX
    Explanations

    special character sequences related to mathematical symbols or expressions

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

    Subscripts in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    indexed variables X_i

    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
     EconPapers
    -0.77
     للمعارف
    -0.73
     transfieras
    -0.71
     <<<<<<<<<<<<<<
    -0.67
    endpush
    -0.65
     bezeichneter
    -0.63
     referrerpolicy
    -0.60
    vax
    -0.59
    bourhood
    -0.59
    లాలు
    -0.59
    POSITIVE LOGITS
    mrow
    0.63
     mattina
    0.52
     căr
    0.49
     Ανακτήθηκε
    0.49
    /></
    0.46
    sizlik
    0.44
     întâ
    0.44
     oamen
    0.43
     acolo
    0.42
     manhã
    0.42
    Activations Density 0.179%

    No Known Activations