© 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. 21-GEMMASCOPE-RES-16K
    11. 1768
    Prev
    Next
    INDEX
    Explanations

    phrases referencing different points of view or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.48
    Advertisement
    -0.44
    itania
    -0.42
    тельстве
    -0.42
    ására
    -0.41
    GeoNames
    -0.41
     rebus
    -0.40
     hesit
    -0.40
     sélectionnez
    -0.40
     متعلقه
    -0.40
    POSITIVE LOGITS
     view
    2.71
    view
    2.28
     View
    2.26
    View
    2.17
     VIEW
    2.15
     views
    2.10
    VIEW
    1.96
     Views
    1.75
    views
    1.73
     VIEWS
    1.60
    Activations Density 0.140%

    No Known Activations