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. 5-GEMMASCOPE-RES-16K
    6. 1958
    Prev
    Next
    INDEX
    Explanations

    references to ghosts or ghost-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.96
     NgModule
    -0.87
     Bowles
    -0.85
    BindingResult
    -0.82
    expandindo
    -0.81
    anyahu
    -0.81
    APN
    -0.80
     estimés
    -0.80
     referenties
    -0.77
    multer
    -0.75
    POSITIVE LOGITS
     ghost
    2.41
     Ghost
    2.20
    ghost
    2.12
    Ghost
    2.07
     ghosts
    2.02
     Ghosts
    1.75
    Ghosts
    1.55
     ghostly
    1.39
     fantasma
    1.34
     fantasmas
    1.30
    Activations Density 0.096%

    No Known Activations