© 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. 16-GEMMASCOPE-RES-16K
    11. 4181
    Prev
    Next
    INDEX
    Explanations

    references to relevant information or entities in a news context

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

    Locations or routes between two endpoints

    np_acts-logits-general · gemini-2.0-flash

    geographic locations and endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.75
     незавершена
    -0.71
     Manly
    -0.67
     Lubbock
    -0.66
     pinulongan
    -0.66
     Taur
    -0.65
    formik
    -0.64
     Guwahati
    -0.64
     Hilo
    -0.63
    enumi
    -0.62
    POSITIVE LOGITS
     nearby
    0.60
     Thompson
    0.59
     Mal
    0.58
    etcode
    0.58
     Roberts
    0.55
     De
    0.54
     THOMPSON
    0.54
    icola
    0.52
     szükség
    0.51
     Pritchard
    0.50
    Activations Density 0.267%

    No Known Activations