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. 6-GEMMASCOPE-RES-16K
    6. 12585
    Prev
    Next
    INDEX
    Explanations

    file extensions and document types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     désolés
    -0.56
     major
    -0.55
     coag
    -0.54
     Paglinawan
    -0.53
    innen
    -0.52
     domestic
    -0.52
     firm
    -0.51
    ')")
    -0.51
    stens
    -0.51
    ierenden
    -0.50
    POSITIVE LOGITS
    qrstuvwxyz
    0.80
    IntoConstraints
    0.79
    ImageField
    0.77
     HasFactory
    0.70
     Obrador
    0.64
     BorderSide
    0.63
    enderror
    0.62
    ainville
    0.60
    lgari
    0.60
    urlpatterns
    0.59
    Activations Density 0.100%

    No Known Activations