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. 7627
    Prev
    Next
    INDEX
    Explanations

    references to the name "Nelson" and associated personal names

    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
     frescas
    -0.82
    ->__
    -0.80
    raim
    -0.77
     mož
    -0.74
    ̓
    -0.70
     fraiche
    -0.70
     Verdad
    -0.70
     inse
    -0.69
     Catto
    -0.67
    jsdelivr
    -0.66
    POSITIVE LOGITS
    Tikang
    1.04
    SharedCtor
    0.97
    blockList
    0.88
    ichy
    0.77
     []:
    0.77
     Charles
    0.76
    Controllo
    0.75
     CHARLES
    0.72
    tocks
    0.72
     resourceCulture
    0.72
    Activations Density 0.617%

    No Known Activations