© 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. 463
    Prev
    Next
    INDEX
    Explanations

    syntax related to functions and methods in programming code

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

    Mathematical or scientific notation/formulae

    np_acts-logits-general · gemini-2.0-flash

    variation, CO2

    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
     -
    -0.40
     ...
    -0.39
     «
    -0.38
     Le
    -0.38
    lers
    -0.38
     ri
    -0.38
      
    -0.38
    et
    -0.37
     
    -0.37
     i
    -0.37
    POSITIVE LOGITS
     مرئيه
    1.11
    AndEndTag
    1.11
     Roskov
    1.11
    évaluateur
    1.04
    findpost
    1.02
    AxisAlignment
    0.98
    GraphicsUnit
    0.98
    NameInMap
    0.95
    Vidite
    0.94
     propOrder
    0.93
    Activations Density 0.080%

    No Known Activations