© 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. 27-GEMMASCOPE-RES-16K
    6. 9150
    Prev
    Next
    INDEX
    Explanations

    aspirational expressions related to future plans and desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    licing
    -0.38
    TintMode
    -0.37
     resultCode
    -0.36
     fö
    -0.36
    hatenablog
    -0.36
    roek
    -0.35
    openqa
    -0.35
    argout
    -0.35
    lica
    -0.34
     tercio
    -0.34
    POSITIVE LOGITS
     someday
    2.08
     future
    1.71
     eventually
    1.56
    future
    1.54
    いつか
    1.45
    Someday
    1.45
     irgendwann
    1.45
    eventually
    1.39
    Future
    1.35
    Eventually
    1.34
    Activations Density 0.652%

    No Known Activations