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. 3-GEMMASCOPE-RES-16K
    6. 11021
    Prev
    Next
    INDEX
    Explanations

    mentions of ghosts and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.89
    #+#
    -0.87
    ſelf
    -0.85
     Roskov
    -0.84
     itſelf
    -0.80
     архивлан
    -0.80
    multer
    -0.79
     myſelf
    -0.76
     indisponible
    -0.75
     Jop
    -0.74
    POSITIVE LOGITS
     ghost
    2.99
    ghost
    2.68
     Ghost
    2.68
    Ghost
    2.54
     ghosts
    2.49
     Ghosts
    2.06
    Ghosts
    1.86
     fantasma
    1.84
     ghostly
    1.78
     fantasmas
    1.75
    Activations Density 0.154%

    No Known Activations