© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10875
    Prev
    Next
    INDEX
    Explanations

    references to the sun and its associated phenomena

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

    "Sun" or related terms

    np_acts-logits-general · gemini-2.0-flash

    sun, solar, sun-related phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.65
    BufferException
    -0.53
     Савезне
    -0.53
     ExecuteAsync
    -0.52
    optionalTypeArgs
    -0.49
    featureID
    -0.49
    tagHelperRunner
    -0.48
    LookAnd
    -0.47
     مرئيه
    -0.47
    цездатний
    -0.46
    POSITIVE LOGITS
     Sun
    0.96
    Sun
    0.90
     SUN
    0.85
     sun
    0.77
     Solar
    0.76
    SUN
    0.76
     Sonnen
    0.76
    sun
    0.73
    Solar
    0.73
     solar
    0.73
    Activations Density 0.072%

    No Known Activations