© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 165
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas related to probabilities and statistical models

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    exponential functions and expressions

    np_acts-logits-general · gemini-2.0-flash

    exponentially growing functions

    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
    Negative Logits
    farwyddwr
    -0.56
     betweenstory
    -0.54
    getResultList
    -0.48
    KommentareTeilen
    -0.47
    няка
    -0.46
     Samaria
    -0.46
     DbSet
    -0.46
    ριν
    -0.44
     viewDidLoad
    -0.44
    cesz
    -0.43
    POSITIVE LOGITS
     exp
    1.34
    exp
    1.30
     exponential
    1.19
     expon
    1.07
    Exp
    1.05
     Exp
    1.03
    EXP
    1.01
     Exponential
    1.00
    expo
    0.98
     power
    0.97
    Activations Density 1.807%

    No Known Activations