© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14136
    Prev
    Next
    INDEX
    Explanations

    descriptions of tension and drama in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.76
     étoient
    -0.62
    AndEndTag
    -0.61
     ſch
    -0.61
     ſche
    -0.60
     ſen
    -0.60
     eſt
    -0.57
     étoit
    -0.57
     ſon
    -0.56
    JScrollPane
    -0.56
    POSITIVE LOGITS
     brilliantly
    0.54
     skil
    0.54
     superbly
    0.51
    /*---
    0.50
    ⇑
    0.50
    bri
    0.49
     somewhat
    0.48
     excellent
    0.48
     masterful
    0.48
     cleverly
    0.47
    Activations Density 0.325%

    No Known Activations