© 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. 3745
    Prev
    Next
    INDEX
    Explanations

    patterns or symbols representing negative values

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

    Hyphens surrounded by various characters

    np_acts-logits-general · gemini-2.0-flash

    code and punctuation fragments

    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
    TagMode
    -0.88
    —
    -0.72
    Архівовано
    -0.68
    liothèque
    -0.65
     DbContext
    -0.63
     ***!
    -0.63
    ……」
    -0.61
    жки
    -0.60
    〝
    -0.60
    ,
    -0.59
    POSITIVE LOGITS
    ----------------
    1.76
    ---------------
    1.30
    awtextra
    1.15
    //-
    0.96
    &-
    0.94
    .-"
    0.91
     -}
    0.87
    ">-
    0.85
    /-
    0.84
    ˏ
    0.84
    Activations Density 0.401%

    No Known Activations