© 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. 463
    Prev
    Next
    INDEX
    Explanations

    references to plans or planning in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of plans or planning concepts

    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
    enderror
    -0.77
    ISTICS
    -0.72
    ICULO
    -0.72
     समीक्षक
    -0.71
    جستارهای
    -0.71
    vener
    -0.70
    }}]{
    -0.69
     précie
    -0.69
    Viited
    -0.69
    accueil
    -0.69
    POSITIVE LOGITS
     plan
    2.25
     PLAN
    2.19
     Plan
    2.15
    plan
    2.13
    Plan
    2.04
     plans
    1.99
     Plans
    1.87
    plans
    1.80
    PLAN
    1.75
     PLANS
    1.74
    Activations Density 0.073%

    No Known Activations