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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53171
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic issues and corporate accountability

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

    but is, scope for, majority of

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    tagHelperRunner
    -0.87
    WriteTagHelper
    -0.82
     CreateTagHelper
    -0.80
     متعلقه
    -0.79
     चीज़ों
    -0.79
    setVerticalGroup
    -0.77
     Мексичка
    -0.77
    IUrlHelper
    -0.69
    XmlAccessorType
    -0.69
    ControllerAdvice
    -0.67
    POSITIVE LOGITS
    Numbers
    0.47
     Zahlen
    0.45
     Cryst
    0.45
     Geste
    0.44
     Granite
    0.44
    gema
    0.43
     Hamm
    0.42
     Jeux
    0.42
     Chancellor
    0.42
     Council
    0.42
    Activations Density 0.040%

    No Known Activations