© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5351
    Prev
    Next
    INDEX
    Explanations

    references to different types or attributes of lenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.58
     zapach
    -0.55
    TiO
    -0.52
     financières
    -0.51
     minat
    -0.51
     Keene
    -0.50
     ogn
    -0.50
     pasi
    -0.50
     betrek
    -0.48
    Besos
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.88
    🏻
    0.86
    GraphicsUnit
    0.81
    🏼
    0.80
     lens
    0.76
    🏽
    0.74
     isInitialized
    0.73
     grades
    0.72
     Lens
    0.72
    WriteAttribute
    0.70
    Activations Density 0.249%

    No Known Activations