© 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. 11555
    Prev
    Next
    INDEX
    Explanations

    elements or attributes related to HTML and code structure

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

    Code or configuration file changes

    np_acts-logits-general · gemini-2.0-flash

    code and foreign languages

    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
    IContainer
    -0.55
    OGND
    -0.51
    nolia
    -0.51
    URLConnection
    -0.47
     etc
    -0.47
    gemeinden
    -0.47
    Filmographie
    -0.47
    ReusableCell
    -0.46
    documentclass
    -0.46
     fre
    -0.46
    POSITIVE LOGITS
    Chham
    0.57
     isNameExpr
    0.56
     proprement
    0.56
     Wikimedijinoj
    0.55
     <<<<<<<<<<<<<<
    0.53
    ":["
    0.52
    országban
    0.52
     Houſe
    0.52
    Diweddarwch
    0.52
     ſta
    0.51
    Activations Density 0.074%

    No Known Activations