© 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. 706
    Prev
    Next
    INDEX
    Explanations

    advice and guidance related to computing issues

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

    Non-English words or phrases

    np_acts-logits-general · gemini-2.0-flash

    prepositions of direction

    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
     kasarigan
    -0.81
     defaultstate
    -0.72
    ContentAlignment
    -0.59
    __).
    -0.56
     dAtA
    -0.55
     تضيفلها
    -0.52
     AssemblyCulture
    -0.51
     beginnetje
    -0.51
    InSection
    -0.50
    abestanden
    -0.48
    POSITIVE LOGITS
     kepada
    1.59
     unto
    1.58
    tothe
    1.53
     thereto
    1.39
    到
    1.32
     к
    1.32
     đến
    1.25
     aos
    1.23
     vnto
    1.23
     aux
    1.22
    Activations Density 0.056%

    No Known Activations