© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6283
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or doubt regarding information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     rękaw
    -0.45
     Accesorios
    -0.45
     nincs
    -0.44
    MessageTagHelper
    -0.43
     územ
    -0.43
    ɟ
    -0.42
     toallas
    -0.42
     auroit
    -0.42
    kamers
    -0.41
     coscienza
    -0.40
    POSITIVE LOGITS
    ViewImports
    0.57
     createSlice
    0.53
    providedIn
    0.48
    lwjgl
    0.47
     محفوظة
    0.45
    ніципалі
    0.45
    IContainer
    0.43
     AttributeSet
    0.42
     arşivlendi
    0.42
    boutin
    0.41
    Activations Density 0.490%

    No Known Activations