Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11117
    Prev
    Next
    INDEX
    Explanations

    words related to specific types of food or culinary terms

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

    Tokens starting with "fr"

    np_acts-logits-general · gemini-2.0-flash

    fr words

    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
    قایناقلار
    -0.52
     pylori
    -0.51
    verwijspagina
    -0.51
     Secret
    -0.50
     برابوك
    -0.49
    ContentAlignment
    -0.48
    adjoint
    -0.47
     secret
    -0.47
     Snyder
    -0.47
    ollectionView
    -0.46
    POSITIVE LOGITS
     Fra
    0.64
     fra
    0.61
     CGRectMake
    0.60
    Fra
    0.58
    GraphicsUnit
    0.58
    ⓧ
    0.58
     disambiguazione
    0.55
    ContentAsync
    0.54
    TagMode
    0.54
     FRA
    0.54
    Activations Density 0.124%

    No Known Activations