© 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. 3-GEMMASCOPE-RES-16K
    11. 8585
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and descriptions of physical locations or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.49
     hurricane
    -0.49
    MENAFN
    -0.49
    HostException
    -0.48
    readObject
    -0.46
    GraphicsUnit
    -0.45
    Nuorodos
    -0.44
    angliski
    -0.43
     Italijanski
    -0.43
     typhoon
    -0.43
    POSITIVE LOGITS
     exterior
    0.81
     outer
    0.74
     edges
    0.68
     underside
    0.67
     front
    0.65
     outermost
    0.64
    exterior
    0.63
     interior
    0.62
     exteriores
    0.62
     côtés
    0.60
    Activations Density 0.906%

    No Known Activations