Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13354
    Prev
    Next
    INDEX
    Explanations

    words related to emotions and personal feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuccessListener
    -0.75
     mxArray
    -0.73
     Bourgoin
    -0.71
     var
    -0.67
     CYTHON
    -0.59
     تضيفلها
    -0.57
    étape
    -0.57
    ValueStyle
    -0.56
     basic
    -0.56
     Lightboxes
    -0.56
    POSITIVE LOGITS
     Reſ
    0.79
     anún
    0.78
     Houſe
    0.78
     Anſ
    0.75
     Cæsar
    0.75
     hunne
    0.73
     $_(
    0.73
     ſeveral
    0.72
     Inſ
    0.72
     dezelve
    0.72
    Activations Density 0.870%

    No Known Activations