© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 12019
    Prev
    Next
    INDEX
    Explanations

    references to thin materials or layers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.98
     resourceCulture
    -0.90
    AutoScale
    -0.90
     Roskov
    -0.89
    AnchorTagHelper
    -0.87
     <<<<<<<<<<<<<<
    -0.87
    ⓧ
    -0.86
    ThroughAttribute
    -0.85
    iquest
    -0.84
     الحره
    -0.84
    POSITIVE LOGITS
     thin
    1.42
     Thin
    1.33
    Thin
    1.32
     thickness
    1.17
    thin
    1.09
     thick
    1.05
     Thickness
    1.04
     thinner
    1.03
     thicker
    0.99
    Thick
    0.94
    Activations Density 0.150%

    No Known Activations