© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references

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

    Numbers followed by units or symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    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
     thousands
    -1.59
     thousand
    -1.43
     Thousands
    -1.34
     THOUS
    -1.28
    thousands
    -1.23
     hundreds
    -1.21
    Thousands
    -1.19
     millions
    -1.17
    thousand
    -1.15
     Thousand
    -1.11
    POSITIVE LOGITS
    exitRule
    0.65
    endpush
    0.61
    Referencie
    0.60
    InjectAttribute
    0.55
    vokat
    0.55
    contentLoaded
    0.53
     незавершена
    0.52
     belas
    0.52
     paio
    0.51
    GOTREF
    0.51
    Activations Density 0.885%

    No Known Activations