© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13098
    Prev
    Next
    INDEX
    Explanations

    terms related to micronutrient deficiencies and their impacts on health

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

    Problems, failures, and deficiencies

    np_acts-logits-general · gemini-2.0-flash

    conditions or problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.86
     Monfieur
    -0.85
     themſelves
    -0.81
     himſelf
    -0.81
     purpoſe
    -0.80
     whoſe
    -0.80
     Anſ
    -0.78
     chofe
    -0.77
     Jefus
    -0.76
     reaſon
    -0.76
    POSITIVE LOGITS
     problems
    0.77
     failure
    0.76
    sizlik
    0.70
     mis
    0.68
     imbalance
    0.64
     error
    0.63
     dysfunction
    0.62
     violation
    0.62
     issues
    0.62
     failures
    0.61
    Activations Density 0.946%

    No Known Activations