© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6446
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to sports, entertainment, and military contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ema
    -0.78
     Ponds
    -0.72
     Lansing
    -0.70
     ISU
    -0.69
    ModelMap
    -0.68
     Alam
    -0.66
     Sina
    -0.65
    naments
    -0.65
     Lizard
    -0.64
     Albright
    -0.64
    POSITIVE LOGITS
     Robson
    0.77
     throm
    0.71
     Atlas
    0.69
    ATLAS
    0.68
     surf
    0.68
     Blake
    0.67
     cocaine
    0.66
    EDEFAULT
    0.66
    Atlas
    0.65
    rus
    0.64
    Activations Density 3.164%

    No Known Activations