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. 12-GEMMASCOPE-RES-16K
    6. 619
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their affiliations or roles in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.83
    AndEndTag
    -0.81
    ImageContext
    -0.80
    BufferException
    -0.76
     saites
    -0.76
    ituaries
    -0.72
    MLLoader
    -0.72
    
    -0.72
     isComment
    -0.68
     Baillargeon
    -0.66
    POSITIVE LOGITS
     Nigeria
    1.00
    Nigeria
    0.93
     Nigerian
    0.91
     Nigerians
    0.83
     Lagos
    0.81
    Nigerian
    0.79
     Ogun
    0.75
     naira
    0.71
     niger
    0.68
     Abuja
    0.67
    Activations Density 0.061%

    No Known Activations