© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 799
    Prev
    Next
    INDEX
    Explanations

    questions that express skepticism or inquiry about opinions and perspectives

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

    really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.65
    ConstraintMaker
    -0.51
    tangentMode
    -0.48
    ➌
    -0.45
    InitVars
    -0.44
     iż
    -0.44
    enumii
    -0.44
    enumi
    -0.43
    UnusedPrivate
    -0.43
    فحة
    -0.42
    POSITIVE LOGITS
     really
    2.14
    Really
    1.96
    really
    1.91
     Really
    1.89
     REALLY
    1.59
     realmente
    1.58
     vraiment
    1.48
     wirklich
    1.46
    真的
    1.40
     davvero
    1.34
    Activations Density 0.069%

    No Known Activations