© 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. 10474
    Prev
    Next
    INDEX
    Explanations

    references to risk factors associated with health conditions

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

    Preceding words like "to", "the", or "within"

    np_acts-logits-general · gemini-2.0-flash

    concluded otherwise

    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
     people
    -0.61
     because
    -0.54
     diferente
    -0.47
     different
    -0.45
     is
    -0.42
     when
    -0.41
     if
    -0.41
    different
    -0.40
     benutzen
    -0.40
     différent
    -0.40
    POSITIVE LOGITS
     kasarigan
    1.10
    niſſe
    1.05
    rungsseite
    1.05
    IsMutable
    1.02
    iſchen
    1.02
    ſſung
    1.01
    AsUp
    1.01
    ſicht
    1.00
     nahilalakip
    0.96
    iſche
    0.95
    Activations Density 10.177%

    No Known Activations