Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8568
    Prev
    Next
    INDEX
    Explanations

    references to light and illumination, particularly in the context of various lighting technologies and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
    WebElementEntity
    -0.51
    UnusedPrivate
    -0.50
    MockMvc
    -0.47
    FieldBuilder
    -0.47
    cipar
    -0.46
    principalColumn
    -0.46
     transfieras
    -0.43
     betweenstory
    -0.43
    ynb
    -0.41
     mergeFrom
    -0.39
    POSITIVE LOGITS
     light
    3.02
     Light
    2.88
    light
    2.86
     LIGHT
    2.86
    Light
    2.81
     lights
    2.77
    LIGHT
    2.67
    lights
    2.61
     lighting
    2.59
     Lights
    2.58
    Activations Density 0.265%

    No Known Activations