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-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1023
    Prev
    Next
    INDEX
    Explanations

    references to socioeconomic difficulties and inequalities in different populations

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

    demographics and their living situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.71
    ագրություններ
    -0.50
    Filmografie
    -0.48
    Enllaces
    -0.45
    phazard
    -0.44
     مرئيه
    -0.44
     يتيمه
    -0.44
    XmlAccessorType
    -0.41
     inapropiados
    -0.40
     Martel
    -0.40
    POSITIVE LOGITS
     citizens
    0.61
     households
    0.60
     household
    0.54
     citizen
    0.54
     residents
    0.52
     living
    0.50
    居民
    0.50
    citizens
    0.49
     Citizens
    0.48
     Households
    0.47
    Activations Density 0.090%

    No Known Activations