© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2725
    Prev
    Next
    INDEX
    Explanations

    expressions of acknowledgment or approval, particularly the word "OK."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.71
     Réponses
    -0.69
    ValueStyle
    -0.67
    Lähteet
    -0.65
    ochet
    -0.61
    FormTagHelper
    -0.60
    Pyx
    -0.58
     ostavi
    -0.56
    astéroïdes
    -0.52
    Dislikes
    -0.51
    POSITIVE LOGITS
     OK
    0.83
    OK
    0.82
    okay
    0.78
     okay
    0.77
    Okay
    0.76
     ok
    0.75
    ok
    0.73
     OKAY
    0.71
     Okay
    0.71
    (!__
    0.69
    Activations Density 0.077%

    No Known Activations