© 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. 36-GEMMASCOPE-RES-16K
    6. 15405
    Prev
    Next
    INDEX
    Explanations

    references to cars and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mieszkanie
    -0.44
    يكب
    -0.35
     feiner
    -0.35
     INSTALL
    -0.34
    illige
    -0.34
    Quy
    -0.34
    飛行機
    -0.33
     pesawat
    -0.33
     coarse
    -0.33
    Ships
    -0.32
    POSITIVE LOGITS
     parked
    1.18
     towed
    0.70
     parkir
    0.69
     estacion
    0.65
     fleet
    0.64
     park
    0.60
     registration
    0.59
     parking
    0.59
    AsUp
    0.58
     stationed
    0.58
    Activations Density 0.292%

    No Known Activations