© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5056
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and properties related to functions, polynomials, and linear algebra

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

    Followed by mathematical terms

    np_acts-logits-general · gemini-2.0-flash

    a followed by mathematical terms

    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
    IonicModule
    -0.49
    jaz
    -0.47
    Przypisy
    -0.47
    ischem
    -0.46
     poveznice
    -0.45
     patate
    -0.45
     Immort
    -0.45
    prong
    -0.43
     patata
    -0.42
    cill
    -0.42
    POSITIVE LOGITS
    Filmografia
    0.71
     nonnegative
    0.68
     positive
    0.66
    prefixer
    0.66
     sequence
    0.61
    ochlor
    0.60
    jabi
    0.59
     finite
    0.59
     integer
    0.59
    resizingMask
    0.58
    Activations Density 1.306%

    No Known Activations