© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8878
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'wholeness' or completeness

    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
     Réponses
    -0.74
     DataTypes
    -0.68
    '",
    -0.68
    Cuisine
    -0.67
     limestones
    -0.67
    ic
    -0.65
    Ellis
    -0.64
     DiCaprio
    -0.63
     dci
    -0.63
     pusher
    -0.62
    POSITIVE LOGITS
     whole
    1.82
    whole
    1.80
     entire
    1.77
    Whole
    1.75
     WHOLE
    1.68
     Whole
    1.67
    entire
    1.47
     Entire
    1.45
     ENTIRE
    1.38
    Entire
    1.33
    Activations Density 0.056%

    No Known Activations