© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    references to academic articles and their citations

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

    "doi" and numbers

    np_acts-logits-general · gemini-2.0-flash

    digital object identifiers

    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
     ExecuteAsync
    -0.88
    RenderAtEndOf
    -0.80
     فريبيس
    -0.79
    mybatisplus
    -0.76
     invokingState
    -0.74
     pleaſure
    -0.70
     SEDS
    -0.70
    MessageTagHelper
    -0.69
    omitempty
    -0.68
    wnież
    -0.68
    POSITIVE LOGITS
    /
    0.51
    Doi
    0.51
    doi
    0.49
    DOI
    0.46
    허
    0.45
     doi
    0.45
    1
    0.43
    .
    0.43
    lo
    0.40
     лю
    0.40
    Activations Density 0.103%

    No Known Activations