© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11433
    Prev
    Next
    INDEX
    Explanations

    terms related to the visibility and clarity of text in documents

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

    Text representation (handwritten, font, letters)

    np_acts-logits-general · gemini-2.0-flash

    handwritten letters and scripts

    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
    TargetException
    -0.57
     polaire
    -0.49
     }}"></
    -0.48
    formik
    -0.48
     BoxDecoration
    -0.48
    SPATH
    -0.47
    cloudfront
    -0.46
    HttpFoundation
    -0.46
    UnitTesting
    -0.46
    marshaller
    -0.45
    POSITIVE LOGITS
     handwriting
    1.39
     writing
    1.26
     script
    1.19
     cursive
    1.14
    writing
    1.11
     alphabet
    1.11
     written
    1.09
     letters
    1.09
     legible
    1.07
     handwritten
    1.07
    Activations Density 0.246%

    No Known Activations