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. 25-GEMMASCOPE-RES-16K
    6. 5977
    Prev
    Next
    INDEX
    Explanations

    concepts related to inclusivity and representation within media and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.73
    AddressBook
    -0.64
     organist
    -0.63
    
    -0.60
    OGND
    -0.60
    Geografía
    -0.59
    Tikang
    -0.56
    Clik
    -0.53
    sidemargin
    -0.53
    存于互联网档案馆
    -0.53
    POSITIVE LOGITS
     art
    1.21
     artistic
    1.04
     expression
    1.00
     artistry
    1.00
     creativity
    0.90
     artwork
    0.87
    art
    0.86
    artistic
    0.86
     artworks
    0.86
     creative
    0.86
    Activations Density 0.317%

    No Known Activations