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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 452
    Prev
    Next
    INDEX
    Explanations

    elements that are programmatically defined or related to digital interactions

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

    Mathematical or code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    mixed language and symbols

    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
    MLLoader
    -0.57
     forms
    -0.49
    Aiheesta
    -0.47
    indakan
    -0.47
    ocities
    -0.46
    ourcen
    -0.46
    艋
    -0.46
    documentclass
    -0.45
     cay
    -0.45
    стя
    -0.44
    POSITIVE LOGITS
    BeginContext
    0.75
    脚注の使い方
    0.66
    ########.
    0.65
    PageContext
    0.61
     المعيارى
    0.58
    ,:);
    0.57
    DoubleQuotes
    0.57
     ErrInvalid
    0.55
    ftagPool
    0.55
    InitVars
    0.52
    Activations Density 0.031%

    No Known Activations