© 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. 15407
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceeding expectations or standards

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

    followed by "more", "beyond", or similar comparatives

    np_acts-logits-general · gemini-2.0-flash

    exceeding limits

    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
    MigrationBuilder
    -0.59
    GOTREF
    -0.52
    RenderAtEndOf
    -0.51
    κτή
    -0.51
    keyframes
    -0.47
     Référence
    -0.46
    withIdentifier
    -0.46
     AssemblyCulture
    -0.46
     наконец
    -0.46
    #+#
    -0.45
    POSITIVE LOGITS
     beyond
    2.22
     exceed
    2.20
     exceeding
    2.10
    beyond
    2.09
     exceeds
    2.07
     exceeded
    1.95
     Beyond
    1.88
     BEYOND
    1.87
    Beyond
    1.79
     above
    1.78
    Activations Density 0.590%

    No Known Activations