© 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. 16-GEMMASCOPE-RES-16K
    11. 13559
    Prev
    Next
    INDEX
    Explanations

    items related to health, medical conditions, and various forms of evaluation or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by conjunctions or commas

    np_acts-logits-general · gemini-2.0-flash

    health and population

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.54
    /
    -0.49
     ordinaires
    -0.49
     esquerdo
    -0.48
     appartiennent
    -0.47
     därför
    -0.47
     francês
    -0.46
     derfor
    -0.46
     purtroppo
    -0.45
    -/
    -0.45
    POSITIVE LOGITS
     samt
    0.84
    리고
    0.83
    力和
    0.83
    人和
    0.82
    性和
    0.82
    以及
    0.82
    +#+#
    0.82
     그리고
    0.78
     וכן
    0.76
     oraz
    0.76
    Activations Density 1.170%

    No Known Activations