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. 52939
    Prev
    Next
    INDEX
    Explanations

    phrases related to burdens and resource consumption

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

    resource consumption and occupation

    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
    Vidite
    -0.67
    ########.
    -0.59
     &___
    -0.52
     OMITTED
    -0.50
    #
    -0.50
     gyhoeddwyd
    -0.49
     JOUR
    -0.47
    дка
    -0.47
    naya
    -0.46
     Digital
    -0.46
    POSITIVE LOGITS
     resource
    0.69
     ressource
    0.68
    resource
    0.68
    featureID
    0.67
     clogging
    0.66
     clog
    0.63
     RESOURCE
    0.63
    Resource
    0.62
     ressources
    0.61
     GenerationType
    0.60
    Activations Density 0.215%

    No Known Activations