© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    a mix of precursory and transitional phrases related to relationships and interactions

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

    "all" (often following prepositions)

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by all

    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
     '\\;'
    -0.99
    principalColumn
    -0.79
    GEBURTSDATUM
    -0.79
    webElementXpaths
    -0.78
    mybatisplus
    -0.75
     الحره
    -0.75
    Chaque
    -0.71
    Cada
    -0.70
    UrlResolution
    -0.70
    owohl
    -0.68
    POSITIVE LOGITS
     all
    3.64
    all
    3.02
    All
    2.51
     All
    2.48
     ALL
    2.33
    ALL
    2.12
     все
    1.93
     semua
    1.76
     allemaal
    1.61
     alls
    1.60
    Activations Density 0.662%

    No Known Activations