© 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. 5-GEMMASCOPE-RES-16K
    11. 1102
    Prev
    Next
    INDEX
    Explanations

    concentration measurements of biochemical substances in a quantitative format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relâche
    -0.49
    cnica
    -0.49
    ינוך
    -0.48
    ED
    -0.47
    Recently
    -0.46
    خاص
    -0.45
    neum
    -0.44
    ziplin
    -0.44
    expandindo
    -0.44
    ρά
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.76
     Obrador
    0.66
    loài
    0.62
     endregion
    0.61
    transQ
    0.61
    HasAnnotation
    0.60
     vettoriale
    0.59
     GenerationType
    0.58
    ANNES
    0.58
     dentaire
    0.57
    Activations Density 0.735%

    No Known Activations