© 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. 3744
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or patterns in a multi-lingual context, particularly focusing on non-English words and structure

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

    HTML or code-related text

    np_acts-logits-general · gemini-2.0-flash

    open source software titles

    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
    PerformLayout
    -0.71
     contextLoads
    -0.70
    ünst
    -0.69
     بيها
    -0.67
     defaultstate
    -0.65
     تانيه
    -0.65
    hülle
    -0.64
     BorderRadius
    -0.63
    انيف
    -0.62
    ensuche
    -0.62
    POSITIVE LOGITS
    ․
    0.53
    oredCriteria
    0.47
    ⓧ
    0.46
    bant
    0.44
     Paglinawan
    0.43
    ・
    0.42
    nthetic
    0.42
    性
    0.42
    úgó
    0.39
    ･
    0.39
    Activations Density 0.002%

    No Known Activations