© 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. 7-GEMMASCOPE-RES-16K
    11. 5551
    Prev
    Next
    INDEX
    Explanations

    comparative language, particularly phrases that denote something being less than another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.77
     myſelf
    -0.71
     purpoſe
    -0.70
     poffe
    -0.69
     HSP
    -0.68
     coö
    -0.68
     itſelf
    -0.68
     EDS
    -0.68
    ſelf
    -0.67
     reafon
    -0.67
    POSITIVE LOGITS
     the
    1.06
    OrEqualTo
    0.90
    writerow
    0.79
     a
    0.77
     what
    0.76
    WebServlet
    0.74
     below
    0.74
     THAN
    0.72
    thenReturn
    0.71
     MainAxisSize
    0.71
    Activations Density 0.157%

    No Known Activations