© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    references to "picture" or "image" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cronin
    -0.51
    Auszeichnungen
    -0.50
    miede
    -0.49
    validators
    -0.48
     dobra
    -0.48
     Gual
    -0.48
     Cobalt
    -0.46
    solete
    -0.46
     Wulf
    -0.46
     helft
    -0.45
    POSITIVE LOGITS
     picture
    1.36
    picture
    1.35
     Picture
    1.32
    Picture
    1.30
     PICTURE
    1.27
    PICTURE
    1.21
     pictures
    1.16
     Pictures
    1.09
    Pictures
    1.09
    pictures
    1.05
    Activations Density 0.041%

    No Known Activations