© 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. 24-GEMMASCOPE-RES-16K
    11. 9689
    Prev
    Next
    INDEX
    Explanations

    references to fictional works and related elements

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

    Punctuation after specific words (USA, sic, FALSE, html, relationship)

    np_acts-logits-general · gemini-2.0-flash

    USA, Germany, relationship, sic, FALSE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     red
    -0.54
    HideFlags
    -0.53
    inku
    -0.52
     multi
    -0.52
     grand
    -0.52
     col
    -0.52
     information
    -0.52
    awtextra
    -0.52
     general
    -0.52
     multiple
    -0.51
    POSITIVE LOGITS
     مشين
    0.76
     presentazione
    0.63
     clínicos
    0.59
    seamnă
    0.59
     courants
    0.58
    .)
    0.58
     ciascuno
    0.58
     deschis
    0.58
    ))
    0.57
     précédents
    0.57
    Activations Density 0.679%

    No Known Activations