© 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. 12894
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and bodies of water

    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
     Roskov
    -0.85
    ########.
    -0.76
     protoimpl
    -0.56
    SharedDtor
    -0.55
    IMPORTED
    -0.53
     насељу
    -0.52
    SuspendLayout
    -0.51
    enderror
    -0.51
     CURIAM
    -0.50
    WidgetItem
    -0.50
    POSITIVE LOGITS
     ocean
    1.62
     sea
    1.57
     oceans
    1.54
     seas
    1.36
    ocean
    1.26
     Atlantic
    1.23
    sea
    1.23
     Ocean
    1.23
     Sea
    1.21
     seawater
    1.15
    Activations Density 0.202%

    No Known Activations