© 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. 962
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically in a structured format

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

    Numbers with hyphens

    np_acts-logits-general · gemini-2.0-flash

    scientific and medical contexts

    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
     كومونز
    -0.73
    featureID
    -0.60
     AssemblyProduct
    -0.50
     well
    -0.47
    ⓧ
    -0.47
     Paused
    -0.44
    nements
    -0.44
     ResourceManager
    -0.44
     تانيه
    -0.43
     pageContext
    -0.43
    POSITIVE LOGITS
    NUMX
    0.79
    DockStyle
    0.76
     réguli
    0.65
    ContentAsync
    0.63
    rungsseite
    0.63
     twill
    0.59
    InSection
    0.59
    IUrlHelper
    0.59
     feroit
    0.58
     fusca
    0.57
    Activations Density 0.630%

    No Known Activations