© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14140
    Prev
    Next
    INDEX
    Explanations

    expressions of authenticity and genuine feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :][
    -0.60
    /**
    -0.56
    ']):
    -0.53
    [])
    -0.52
    hdashline
    -0.51
    Билгалдахарш
    -0.51
    Бахар
    -0.50
     henvisninger
    -0.50
    "]').
    -0.50
    RRect
    -0.49
    POSITIVE LOGITS
     genuinely
    0.93
     truly
    0.92
     realy
    0.90
    actual
    0.87
     really
    0.87
     virkelig
    0.87
     réelle
    0.86
    Truly
    0.86
     réellement
    0.85
    truly
    0.83
    Activations Density 0.373%

    No Known Activations