© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2653
    Prev
    Next
    INDEX
    Explanations

    concepts related to education and social justice initiatives that focus on compassion and respect for diverse communities

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

    following verbs related to betterment/promotion

    np_acts-logits-general · gemini-2.0-flash

    promoting growth and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.53
     flexibilidad
    -0.50
     húmedo
    -0.49
     visst
    -0.48
     gambe
    -0.47
     adequada
    -0.47
     nanti
    -0.47
     Comparing
    -0.46
    afficheront
    -0.46
    Comparing
    -0.46
    POSITIVE LOGITS
     lifestyle
    0.43
     excellence
    0.41
     worldwide
    0.41
    hdashline
    0.40
     solutions
    0.39
     underserved
    0.39
     lende
    0.39
    主に
    0.37
     lifestyles
    0.36
    )_/¯
    0.36
    Activations Density 0.355%

    No Known Activations