© 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. 7028
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, organizations, or entities related to research and academia

    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
    0
    -0.70
    &__
    -0.70
     Allentown
    -0.67
     dusting
    -0.66
    vein
    -0.66
    databind
    -0.66
    ähkö
    -0.65
     dusted
    -0.65
     Dust
    -0.65
     Klin
    -0.64
    POSITIVE LOGITS
     DialogInterface
    0.80
     المعيارى
    0.77
     kasarigan
    0.76
     DCM
    0.75
    ergies
    0.75
     betweenstory
    0.74
     ARA
    0.74
     Allez
    0.72
    TargetException
    0.71
     Nuo
    0.71
    Activations Density 2.147%

    No Known Activations