Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13396
    Prev
    Next
    INDEX
    Explanations

    references to bottles

    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
     subsidi
    -0.55
     Haller
    -0.53
    grain
    -0.48
    美味しかったです
    -0.48
    이
    -0.48
     matar
    -0.46
    pecha
    -0.46
    cerna
    -0.45
     births
    -0.45
     tamu
    -0.45
    POSITIVE LOGITS
     bottle
    1.04
     bottles
    0.92
     Bottle
    0.91
    "]);
    
    0.88
    ViewFeatures
    0.82
     botella
    0.81
    bottle
    0.79
    Bottle
    0.78
     BOTT
    0.78
     }],
    0.78
    Activations Density 0.050%

    No Known Activations