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. 11193
    Prev
    Next
    INDEX
    Explanations

    phrases related to vehicle recalls and safety notices

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

    Something is broken/wrong with a car part

    np_acts-logits-general · gemini-2.0-flash

    broken hub

    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
    tagHelperRunner
    -0.70
    ⓧ
    -0.68
    RegistryLite
    -0.63
    Geplaatst
    -0.62
    WindowConstants
    -0.60
     autorytatywna
    -0.60
    AutoScaleMode
    -0.54
    ГЛА
    -0.53
     Réponses
    -0.53
    RegressionTest
    -0.51
    POSITIVE LOGITS
     rubber
    0.71
     plastic
    0.71
     retaining
    0.67
    plastic
    0.62
     grom
    0.60
     retainer
    0.59
    rubber
    0.57
     plástico
    0.56
     Rubber
    0.56
     plastik
    0.55
    Activations Density 0.314%

    No Known Activations