© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3740
    Prev
    Next
    INDEX
    Explanations

    elements related to image attributes and processing in code snippets

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

    Image resizing, cropping, and format conversions

    np_acts-logits-general · gemini-2.0-flash

    image sizing and filters

    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
     typelib
    -0.61
    RTCK
    -0.61
     separating
    -0.53
     Bastille
    -0.53
     tren
    -0.52
     åt
    -0.52
    enment
    -0.52
     autorytatywna
    -0.52
    stown
    -0.51
     McCann
    -0.50
    POSITIVE LOGITS
     crop
    0.64
    fit
    0.63
     fit
    0.63
    SizeMode
    0.63
     BoxFit
    0.63
    Tikang
    0.61
     cropping
    0.57
    Fit
    0.55
     FIT
    0.55
     aspect
    0.53
    Activations Density 0.131%

    No Known Activations