© 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. 8577
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their properties

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

    Code, data, names, and values

    np_acts-logits-general · gemini-2.0-flash

    assignments and equality checks

    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
     AssemblyCulture
    -0.75
     يتيمه
    -0.69
    OGND
    -0.65
    rrggbb
    -0.64
     ويكيميديا
    -0.62
    aderie
    -0.60
     Forder
    -0.60
    olymer
    -0.60
    Vidite
    -0.59
    ########.
    -0.59
    POSITIVE LOGITS
     =
    1.28
     ==
    0.79
    return
    0.77
     ===
    0.64
     =>
    0.63
     -
    0.62
     !=
    0.62
     :
    0.61
     –
    0.58
     said
    0.57
    Activations Density 0.227%

    No Known Activations