© 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. 20-GEMMASCOPE-RES-16K
    11. 11956
    Prev
    Next
    INDEX
    Explanations

    logical connectors and transition words in a text

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

    Followed by a mathematical expression

    np_acts-logits-general · gemini-2.0-flash

    logical consequence connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.64
     useRouter
    -0.54
    enumi
    -0.54
    SneakyThrows
    -0.52
     guides
    -0.48
     Cliquez
    -0.48
    AsUp
    -0.48
    ++]=
    -0.48
    ++);
    -0.47
    httphttps
    -0.47
    POSITIVE LOGITS
    MessageOf
    0.77
     we
    0.68
    RegistryLite
    0.63
     quelcon
    0.58
     समीक्षाओं
    0.57
     there
    0.56
     فريبيس
    0.56
     ciasc
    0.55
     FishBase
    0.53
     intuitively
    0.53
    Activations Density 1.655%

    No Known Activations