© 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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11890
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols related to functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.72
     kasarigan
    -0.68
     Chwiliwch
    -0.65
     ivelany
    -0.59
    хьтан
    -0.57
    sizeCache
    -0.57
    principalColumn
    -0.56
    GEBURTSDATUM
    -0.55
     resourceCulture
    -0.54
    PreferredItem
    -0.54
    POSITIVE LOGITS
    ViewImports
    0.49
    medriver
    0.44
    UnifiedTopology
    0.41
     makeStyles
    0.39
    TokenNameLBRACE
    0.36
    kuma
    0.35
    iläum
    0.35
     منها
    0.34
     geo
    0.34
    imageshack
    0.34
    Activations Density 0.942%

    No Known Activations