© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 14593
    Prev
    Next
    INDEX
    Explanations

    references to "vision" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRNewswire
    -0.64
    <tr>
    -0.60
    romole
    -0.60
       
    -0.59
    б
    -0.58
    BS
    -0.57
    âu
    -0.56
    DataMember
    -0.56
    u
    -0.55
    ス
    -0.55
    POSITIVE LOGITS
     VISION
    1.30
     Visions
    1.29
     visions
    1.27
     imagine
    1.20
     imagines
    1.20
     imagining
    1.19
     Vision
    1.16
     IMAG
    1.15
     Imagine
    1.15
     vision
    1.14
    Activations Density 0.100%

    No Known Activations