© 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. 8-GEMMASCOPE-RES-16K
    11. 10862
    Prev
    Next
    INDEX
    Explanations

    phrases indicating signs or indicators of various phenomena or conditions

    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
     שוליים
    -0.90
    ERICK
    -0.78
    enderror
    -0.77
    PerformLayout
    -0.71
    \"");
    -0.71
    athlon
    -0.71
    felder
    -0.71
    rália
    -0.67
    expandindo
    -0.66
    beitung
    -0.66
    POSITIVE LOGITS
     Signs
    1.86
     signs
    1.81
    Signs
    1.77
     SIGNS
    1.72
     Sign
    1.71
     sign
    1.67
     SIGN
    1.64
    signs
    1.60
    sign
    1.60
    Sign
    1.57
    Activations Density 0.079%

    No Known Activations