© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9580
    Prev
    Next
    INDEX
    Explanations

    the presence of the name "El" and its variations, indicating a focus on specific places or entities associated with that term

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

    starting with "El" or "RW"

    np_acts-logits-general · gemini-2.0-flash

    words starting with el

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prácticas
    -0.52
     cálido
    -0.48
     Económica
    -0.47
     herida
    -0.47
     totalidad
    -0.47
    berdayakan
    -0.47
     práctico
    -0.46
     kysy
    -0.46
     detailsNormal
    -0.46
     costumbres
    -0.46
    POSITIVE LOGITS
     EL
    0.63
     el
    0.59
     El
    0.57
     Ell
    0.56
     elm
    0.54
     Elgin
    0.52
     elb
    0.52
     Eld
    0.50
     Ellie
    0.50
     Elin
    0.50
    Activations Density 0.159%

    No Known Activations