© 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. 99
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to constants, variables, and conditionals within a mathematical or statistical context

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

    "For" followed by words like "all," "any," or "some"

    np_acts-logits-general · gemini-2.0-flash

    for all / any / some

    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
     BoxDecoration
    -0.75
     utafitiHapana
    -0.55
    VersionUID
    -0.52
    Glej
    -0.50
     रेटिंग
    -0.49
    UserScript
    -0.49
    ImageContext
    -0.49
     "../../../
    -0.49
    zyż
    -0.48
     فريبيس
    -0.47
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.64
     brev
    0.55
     fixed
    0.55
    fixed
    0.54
     sufficiently
    0.52
    ∀
    0.51
     suffic
    0.51
    QPalette
    0.50
    ylvan
    0.49
     large
    0.49
    Activations Density 0.936%

    No Known Activations