© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3599
    Prev
    Next
    INDEX
    Explanations

    instances of writing-related actions and mentions of written works

    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
    requireNonNull
    -0.72
    djangoproject
    -0.61
    Confirmed
    -0.58
     ThemeData
    -0.58
    oa̍t
    -0.56
     cherchés
    -0.56
    doctype
    -0.56
    illah
    -0.56
     <>",
    -0.55
    RemoveField
    -0.53
    POSITIVE LOGITS
     write
    1.59
     writing
    1.50
     written
    1.49
     wrote
    1.41
    write
    1.41
     writes
    1.41
     Write
    1.35
     Writing
    1.34
     WRITE
    1.33
     écrit
    1.31
    Activations Density 0.231%

    No Known Activations