© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    references to numerical data or metrics in scientific contexts

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

    Measurements in micrometers/microns

    np_acts-logits-general · gemini-2.0-flash

    microscopic scale measurements

    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
     Man
    -0.53
     collè
    -0.51
    ########.
    -0.47
    canestro
    -0.47
    setState
    -0.46
     Bol
    -0.45
    ódz
    -0.45
     Pensacola
    -0.44
     hard
    -0.43
    atcher
    -0.43
    POSITIVE LOGITS
     microns
    1.08
     micron
    1.06
     mic
    1.01
    micron
    0.99
     µ
    0.97
     micro
    0.96
    μ
    0.96
     μ
    0.95
    micro
    0.94
     Micro
    0.86
    Activations Density 0.729%

    No Known Activations