© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12201
    Prev
    Next
    INDEX
    Explanations

    occurrences of names or titles in the text

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

    Non-English characters and diacritics

    np_acts-logits-general · gemini-2.0-flash

    foreign prefixes

    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
    laying
    -0.48
    PYX
    -0.45
     laying
    -0.45
     Exacts
    -0.40
    的问道
    -0.39
     Lac
    -0.39
     sand
    -0.39
     lay
    -0.38
    Lac
    -0.38
    strafe
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.83
     MainAxisSize
    0.73
    AccessorTable
    0.69
     Wikimedijinoj
    0.68
    tagHelperRunner
    0.65
    клопе
    0.65
     Abp
    0.65
    новниш
    0.65
    Хьажоргаш
    0.64
    TERY
    0.63
    Activations Density 0.113%

    No Known Activations