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. 16-GEMMASCOPE-RES-16K
    6. 15862
    Prev
    Next
    INDEX
    Explanations

    terms related to transport and traffic regulations

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

    followed by a time period

    np_acts-logits-general · gemini-2.0-flash

    measurements and quantities

    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
    "]="
    -0.66
    Vidite
    -0.64
    }{*}{
    -0.60
    ')")
    -0.59
    🏽
    -0.58
    )':
    -0.56
    )");
    
    -0.56
    )");
    -0.55
    "]=
    -0.55
    ")(
    -0.55
    POSITIVE LOGITS
    Bioaccumulative
    0.59
     contextLoads
    0.56
    kheim
    0.56
    koin
    0.54
     jsPsych
    0.53
     soon
    0.52
    webElement
    0.51
    writeFieldEnd
    0.50
    rawDesc
    0.50
    RepeatedField
    0.50
    Activations Density 0.571%

    No Known Activations