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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 11088
    Prev
    Next
    INDEX
    Explanations

    features and specifications of a product, particularly focusing on safety ratings and digital displays

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

    Clock-like displays, gauges, and measurement instruments

    np_acts-logits-general · gemini-2.0-flash

    Measuring instrument indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.71
    évaluateur
    -0.59
    CopyWith
    -0.59
    exitRule
    -0.59
    Personendaten
    -0.56
     AssemblyTitle
    -0.54
    ItemLayout
    -0.51
     protoimpl
    -0.51
    HtmlAttribute
    -0.50
    interopRequire
    -0.50
    POSITIVE LOGITS
     dials
    1.04
     dial
    1.00
     clock
    0.98
     needle
    0.93
     meter
    0.91
    meter
    0.90
    needle
    0.84
     gauges
    0.84
    Meter
    0.84
     readout
    0.82
    Activations Density 0.225%

    No Known Activations