© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "soon" or similar time indicators in relation to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    menuStrip
    -0.50
     uygula
    -0.45
     Gewer
    -0.37
     pratiquer
    -0.37
     judiciaire
    -0.35
     citoy
    -0.35
     field
    -0.35
    atyw
    -0.34
    srand
    -0.34
     izquierdo
    -0.34
    POSITIVE LOGITS
     soon
    1.81
    Soon
    1.80
     Soon
    1.75
    soon
    1.68
     SOON
    1.52
     foon
    1.24
     snart
    1.09
    ientôt
    1.07
     shortly
    1.04
     bientôt
    1.02
    Activations Density 0.094%

    No Known Activations