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. 16-GEMMASCOPE-RES-16K
    6. 12032
    Prev
    Next
    INDEX
    Explanations

    instances of significant formatting or structural markers in a document

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

    Non-English characters or symbols

    np_acts-logits-general · gemini-2.0-flash

    Latoya Jackson

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     FetchType
    -0.78
     المعرف
    -0.71
    ImageContext
    -0.71
    MessageState
    -0.70
    hdys
    -0.69
    multer
    -0.69
    prefixer
    -0.68
    PostExecute
    -0.67
    audiovisuel
    -0.66
     opérés
    -0.66
    POSITIVE LOGITS
     
    1.03
    .
    0.86
    
    0.86
    
    0.75
    Jays
    0.61
     morts
    0.57
     szól
    0.56
     jullie
    0.54
     abbiano
    0.53
     mourir
    0.53
    Activations Density 0.149%

    No Known Activations