© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "co-" indicating collaboration or cooperation

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

    starting with "co-" followed by a hyphen

    np_acts-logits-general · gemini-2.0-flash

    joint actions or roles starting with "co"

    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
    twimg
    -0.51
    AddTagHelper
    -0.51
     ITIS
    -0.50
     autorytatywna
    -0.47
     compte
    -0.46
     estimés
    -0.44
    ftagPool
    -0.44
    enol
    -0.43
     dene
    -0.43
    期刊论文
    -0.43
    POSITIVE LOGITS
     chi̍t
    0.67
     StringTokenizer
    0.63
     ordinate
    0.60
    ordinates
    0.59
     HasFactory
    0.58
     ordin
    0.58
     co
    0.57
     Phaser
    0.57
     authored
    0.57
     beden
    0.56
    Activations Density 0.095%

    No Known Activations