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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 10389
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotional experiences or sentiments related to significant life moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.67
    oa̍t
    -0.66
    IntoConstraints
    -0.62
    Jereo
    -0.58
    Viitteet
    -0.57
    PMailer
    -0.56
    WarningLevel
    -0.56
     iParam
    -0.55
    AsUp
    -0.54
    ystema
    -0.53
    POSITIVE LOGITS
     magical
    0.78
     therapeutic
    0.77
     liberating
    0.72
     freeing
    0.68
     magique
    0.67
     terapé
    0.67
     eu
    0.65
     cath
    0.64
     indescribable
    0.64
     mágica
    0.64
    Activations Density 0.237%

    No Known Activations