© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7287
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or references to returning ideas in the text

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

    "Again" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    again, elaboration, clarification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.76
    tvguidetime
    -0.72
     propOrder
    -0.65
     /\.(
    -0.63
    Bibliograf
    -0.62
    phosa
    -0.57
     lenker
    -0.56
    cshtml
    -0.56
    IContainer
    -0.53
    webElement
    -0.52
    POSITIVE LOGITS
    Again
    0.90
     Again
    0.86
     again
    0.78
    again
    0.73
     AGAIN
    0.65
    ruptedException
    0.63
     novamente
    0.62
    AGAIN
    0.60
     reiterate
    0.60
    reiter
    0.59
    Activations Density 0.078%

    No Known Activations