© 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. 11-GEMMASCOPE-RES-16K
    11. 10179
    Prev
    Next
    INDEX
    Explanations

    instances of the word "literally" and related phrases about reality or truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Malley
    -0.51
     ivelany
    -0.47
    adaptiveStyles
    -0.47
    ESOME
    -0.45
     typelib
    -0.45
     дописавши
    -0.44
     ...]
    -0.44
     الرياضيه
    -0.42
    دانشنامهٔ
    -0.41
    
    -0.41
    POSITIVE LOGITS
     literally
    1.59
    Literally
    1.52
     Literally
    1.49
     literalmente
    1.47
     literal
    1.45
    literally
    1.41
     Literal
    1.14
    literal
    1.13
    Literal
    1.03
     LITER
    1.01
    Activations Density 0.136%

    No Known Activations