© 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. 24-GEMMASCOPE-RES-16K
    11. 10076
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their familial relationships

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

    before "and"

    np_acts-logits-general · gemini-2.0-flash

    names followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.60
     propOrder
    -0.59
     Chwiliwch
    -0.57
    RTLR
    -0.57
    pli
    -0.56
    swire
    -0.55
     calendriers
    -0.54
     ProtoMessage
    -0.54
     تضيفلها
    -0.54
    новништво
    -0.53
    POSITIVE LOGITS
     especialidad
    0.35
     volverá
    0.34
     actualización
    0.30
     privées
    0.30
    special
    0.30
    saraba
    0.30
     GenerationType
    0.29
    venidos
    0.29
     mourut
    0.28
     Especial
    0.28
    Activations Density 0.113%

    No Known Activations