© 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. 16-GEMMASCOPE-RES-16K
    11. 1808
    Prev
    Next
    INDEX
    Explanations

    mechanical components and specifications of vehicles

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

    Convertible, foldable, transformable features

    np_acts-logits-general · gemini-2.0-flash

    changeable, foldable, transformable features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     superstitious
    -0.60
     ویکی‌پدی
    -0.59
    specialchars
    -0.59
     RIPRODUZIONE
    -0.56
    ContentAsync
    -0.56
     Sump
    -0.56
    UnknownFieldSet
    -0.55
    TestTools
    -0.55
     smeared
    -0.54
     chrétienne
    -0.54
    POSITIVE LOGITS
     flexibility
    0.83
     versatility
    0.83
     versatile
    0.73
     Flexibility
    0.73
    Flexibility
    0.71
     flexible
    0.70
    
    0.70
     adaptable
    0.70
     adaptability
    0.67
     changeable
    0.66
    Activations Density 0.444%

    No Known Activations