© 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. 3-GEMMASCOPE-RES-16K
    11. 10618
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data or statistical results in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugeot
    -0.96
     $_"
    -0.91
    VERTISEMENT
    -0.90
     FormsModule
    -0.90
     createSprite
    -0.89
    LLocation
    -0.82
    ſſel
    -0.82
     RSITY
    -0.82
    mybatisplus
    -0.81
     ERSITY
    -0.80
    POSITIVE LOGITS
    ↵↵
    2.26
    ↵
    1.65
    ↵↵↵
    1.63
    ↵↵↵↵
    1.53
    <eos>
    1.47
    ↵↵↵↵↵
    1.46
    <h2>
    1.46
    ↵↵↵↵↵↵
    1.34
    [toxicity=0]
    1.29
    <h3>
    1.28
    Activations Density 0.937%

    No Known Activations