Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3002
    Prev
    Next
    INDEX
    Explanations

    numeric values and their formats

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

    Numbers followed by other numbers

    np_acts-logits-general · gemini-2.0-flash

    subtitles, file paths, math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ***!
    -0.64
     vars
    -0.57
    CPtr
    -0.56
    unif
    -0.48
    CppMethod
    -0.48
    Configurator
    -0.46
    Carreira
    -0.44
    sträger
    -0.44
     Serving
    -0.43
    mav
    -0.43
    POSITIVE LOGITS
     المعيارى
    0.80
    Xna
    0.77
     consultato
    0.69
     odkazy
    0.68
     IgA
    0.64
     CURIAM
    0.64
    NameInMap
    0.64
    izr
    0.62
    حوالہ
    0.62
    󠁣
    0.61
    Activations Density 0.258%

    No Known Activations