© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 265
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate explanations or statements being made

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "That said" and similar phrases

    np_acts-logits-general · gemini-2.0-flash

    that said, however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     dă
    -0.33
     comigo
    -0.29
     geschehen
    -0.28
     hängen
    -0.28
     reducido
    -0.28
     izquierdo
    -0.28
     linguistique
    -0.28
    reszcie
    -0.28
    rigkeit
    -0.27
    carteles
    -0.27
    POSITIVE LOGITS
    anmoins
    0.77
     obstante
    0.75
    etheless
    0.71
    uttavia
    0.68
    transQ
    0.67
    MigrationBuilder
    0.65
     Dennoch
    0.65
     Nonetheless
    0.63
    Nonetheless
    0.62
    theless
    0.62
    Activations Density 0.251%

    No Known Activations