© 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. 7-GEMMASCOPE-RES-16K
    11. 8268
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to familiarity and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.89
    +#+#
    -0.85
    بوابة
    -0.81
     متعلقه
    -0.79
     propOrder
    -0.77
    Autoritní
    -0.76
    //
    -0.72
     OTP
    -0.68
     THINK
    -0.68
     kasarigan
    -0.67
    POSITIVE LOGITS
     familiar
    1.22
    familiar
    1.13
     Familiar
    1.00
    Familiar
    1.00
     familiarity
    0.92
     familiare
    0.89
     знако
    0.75
     vertrou
    0.75
     familiari
    0.71
    熟悉
    0.70
    Activations Density 0.106%

    No Known Activations