© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11605
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related phrases concerning data manipulation and array operations

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

    Code snippets using numpy

    np_acts-logits-general · gemini-2.0-flash

    numpy and python code

    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
    StoryboardSegue
    -0.67
    بوابة
    -0.55
    inaison
    -0.52
    astéro
    -0.52
    >{@
    -0.51
    Ami
    -0.49
    eynman
    -0.46
    asanjo
    -0.45
    Geplaatst
    -0.45
    Mutagenicity
    -0.45
    POSITIVE LOGITS
     np
    0.74
    np
    0.71
     NPY
    0.67
     dtype
    0.66
     numpy
    0.62
    +#+#
    0.59
    canestro
    0.56
     NSError
    0.56
     GenerationType
    0.55
    numpy
    0.54
    Activations Density 0.130%

    No Known Activations