© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 71143
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomical measurements and magnitudes

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

    astronomical magnitude and flux measurements

    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
    FormTagHelper
    -0.51
     NSCoder
    -0.47
    SequentialGroup
    -0.45
    VersionUID
    -0.45
    !*\
    -0.45
    ſelf
    -0.44
     createSlice
    -0.42
     resourceCulture
    -0.41
     AssemblyCompany
    -0.41
     springfox
    -0.41
    POSITIVE LOGITS
    UseVisualStyle
    0.47
     grade
    0.47
    ligkeit
    0.46
     shining
    0.42
    grade
    0.42
    fancybox
    0.42
     zijne
    0.41
     avond
    0.41
    enschappe
    0.40
     bintang
    0.40
    Activations Density 0.037%

    No Known Activations