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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38526
    Prev
    Next
    INDEX
    Explanations

    references to light and brightness

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

    sunshine and light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.65
     surla
    -0.60
     Савезне
    -0.60
    icylic
    -0.58
     تكبرها
    -0.58
     <=",
    -0.57
     müſſen
    -0.57
    ReusableCell
    -0.57
    ੝
    -0.55
     disambiguazione
    -0.55
    POSITIVE LOGITS
     sunny
    0.51
     sunshine
    0.46
     spacious
    0.40
     sunlight
    0.40
     room
    0.40
    明るく
    0.39
     cheerful
    0.38
     airy
    0.38
     daylight
    0.38
     rooms
    0.36
    Activations Density 0.003%

    No Known Activations