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

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 9496
    Prev
    Next
    INDEX
    Explanations

    quantitative assessments and qualifiers related to data or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     those
    -0.95
     themselves
    -0.79
    those
    -0.78
     những
    -0.77
    зовые
    -0.74
     paar
    -0.73
     these
    -0.73
     yourselves
    -0.71
     few
    -0.71
    many
    -0.70
    POSITIVE LOGITS
     neuem
    0.93
    __*/
    0.80
     weißem
    0.77
     pouvoirs
    0.76
    ciety
    0.75
    SequentialGroup
    0.75
     gouvernements
    0.74
    ChildScrollView
    0.71
     sentiers
    0.70
     gutem
    0.70
    Activations Density 0.373%

    No Known Activations