© 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. 18-GEMMASCOPE-RES-16K
    11. 15730
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain medical or healthcare-related content

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

    Mathematical or programming-related expressions

    np_acts-logits-general · gemini-2.0-flash

    alopecia areata patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wherewith
    -0.56
    ;
    -0.52
    tys
    -0.52
    faßt
    -0.51
    십시오
    -0.50
     ;
    -0.49
    ;
    -0.47
    dest
    -0.47
     daß
    -0.46
    ty
    -0.45
    POSITIVE LOGITS
    Datuak
    1.36
    .*")]
    1.13
     تانيه
    0.93
     يتيمه
    0.90
    存于互联网档案馆
    0.87
    rungsseite
    0.86
     XNUMX
    0.86
    :✨
    0.86
     Protección
    0.81
     AssemblyProduct
    0.81
    Activations Density 0.038%

    No Known Activations