© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and structure within programming languages

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

    Non-English words or code

    np_acts-logits-general · gemini-2.0-flash

    multilingual technical identifiers

    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
     שוליים
    -0.95
     חיצוניים
    -0.93
    RectangleBorder
    -0.90
     estekak
    -0.88
    OGND
    -0.80
     للمعارف
    -0.79
    ChildScrollView
    -0.76
     otomatig
    -0.74
     كومونز
    -0.74
    InjectAttribute
    -0.72
    POSITIVE LOGITS
     disambiguazione
    0.65
    ксана
    0.53
    Referencie
    0.48
    diğinde
    0.47
     motor
    0.46
     spørs
    0.46
    Warto
    0.44
     akkor
    0.44
    gaard
    0.44
    Rect
    0.43
    Activations Density 0.114%

    No Known Activations