© 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. 10-GEMMASCOPE-RES-16K
    11. 11095
    Prev
    Next
    INDEX
    Explanations

    indicative phrases that suggest a degree of uncertainty or conditionality in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CascadeType
    -0.44
    AxisAlignment
    -0.38
     goodly
    -0.35
    PDATE
    -0.34
     border
    -0.34
     ку
    -0.34
     EXPER
    -0.34
     patri
    -0.34
    engah
    -0.34
     numberWith
    -0.33
    POSITIVE LOGITS
    Derbyniad
    0.58
    SharedDtor
    0.55
    webElementXpaths
    0.54
     مشين
    0.53
    GIVEREF
    0.53
    ViewFeatures
    0.48
    >());
    0.46
     att
    0.45
    icism
    0.45
    νονται
    0.44
    Activations Density 0.991%

    No Known Activations