© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-GEMMASCOPE-RES-16K
    11. 1002
    Prev
    Next
    INDEX
    Explanations

    references to children and the concept of childhood experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mittelt
    -0.30
    N
    -0.29
    up
    -0.29
    RefNanny
    -0.28
    down
    -0.27
     själ
    -0.27
     právě
    -0.27
    Then
    -0.27
     lucru
    -0.27
    then
    -0.26
    POSITIVE LOGITS
    رشف
    0.66
    IsContent
    0.64
     surla
    0.63
    toprule
    0.61
     queſto
    0.61
     BoxFit
    0.60
    principalColumn
    0.60
     utafitiHapana
    0.60
     ✭✭
    0.60
     ProtoMessage
    0.60
    Activations Density 1.338%

    No Known Activations