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. 20-GEMMASCOPE-RES-16K
    6. 6383
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.47
     Cæsar
    -1.44
     itſelf
    -1.42
     myſelf
    -1.41
     Efq
    -1.41
     Diſ
    -1.35
     Houſe
    -1.34
     Anſ
    -1.34
     Reſ
    -1.33
     houſe
    -1.32
    POSITIVE LOGITS
     con
    0.55
     le
    0.54
     una
    0.53
     la
    0.53
     di
    0.51
     è
    0.50
     tras
    0.49
     es
    0.47
     il
    0.47
     punt
    0.45
    Activations Density 0.040%

    No Known Activations