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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8124
    Prev
    Next
    INDEX
    Explanations

    instructions and recommendations related to cleaning and mold prevention

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

    stains and cleaning

    np_acts-logits-general · gemini-2.0-flash

    stains and cleaning

    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
    EndInit
    -0.73
    KommentareTeilen
    -0.68
     виправивши
    -0.65
    BeginInit
    -0.58
     تضيفلها
    -0.58
     adicionais
    -0.57
     femininas
    -0.57
    ruptedException
    -0.54
    engkapi
    -0.53
    tonode
    -0.53
    POSITIVE LOGITS
     stain
    0.93
     stains
    0.89
     stubborn
    0.75
     mancha
    0.72
     cleaning
    0.70
    stain
    0.69
     taches
    0.68
     manchas
    0.68
     Stain
    0.67
     staining
    0.65
    Activations Density 0.109%

    No Known Activations