© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5330
    Prev
    Next
    INDEX
    Explanations

    descriptions of eyes or visual characteristics related to intensity and emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "eyes" or looking

    np_acts-logits-general · gemini-2.0-flash

    descriptions of eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.55
    bcryptjs
    -0.53
     odor
    -0.53
    BASEPATH
    -0.51
     odour
    -0.50
    новништво
    -0.50
     Inbox
    -0.49
    rrggbb
    -0.48
    stateProvider
    -0.48
    IndentedString
    -0.48
    POSITIVE LOGITS
     eyes
    1.05
    eyes
    0.85
     Eyes
    0.85
     eye
    0.83
    Eyes
    0.82
     EYES
    0.80
     ojos
    0.75
     Eye
    0.75
    eye
    0.75
    eyed
    0.74
    Activations Density 0.127%

    No Known Activations