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. 0-GEMMASCOPE-RES-16K
    6. 6344
    Prev
    Next
    INDEX
    Explanations

    terms related to planning and strategic organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.89
     المعيارى
    -0.80
    RemoteException
    -0.80
    kable
    -0.75
     kaldı
    -0.74
     exemplaires
    -0.74
     conservé
    -0.73
     CULTURAL
    -0.72
     Diretto
    -0.72
     légitime
    -0.71
    POSITIVE LOGITS
     Plan
    1.95
     plan
    1.77
    Plan
    1.72
     plans
    1.71
     Plans
    1.61
     planning
    1.54
    PLAN
    1.52
    plan
    1.51
    Plans
    1.50
    plans
    1.48
    Activations Density 0.170%

    No Known Activations