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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16326
    Prev
    Next
    INDEX
    Explanations

    technical terms and code syntax related to software development and programming languages

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

    Protobuf-related code

    np_acts-logits-general · gemini-2.0-flash

    you are

    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
    devamını
    -0.93
     saites
    -0.88
    RenderAtEndOf
    -0.87
    fjspx
    -0.87
    KommentareTeilen
    -0.85
    İstinadlar
    -0.85
     &___
    -0.81
     समीक्षक
    -0.81
    Personensuche
    -0.80
    ValueStyle
    -0.78
    POSITIVE LOGITS
    ſelf
    0.57
    ſelves
    0.53
     quartzite
    0.53
    ATRE
    0.51
     tslint
    0.51
    \<^
    0.51
     folds
    0.51
    BRUARY
    0.49
    ۟
    0.49
    <!--[
    0.49
    Activations Density 0.388%

    No Known Activations