© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2916
    Prev
    Next
    INDEX
    Explanations

    references to timelines and events related to academia and scholarships

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

    Years (especially around 2010-2020)

    np_acts-logits-general · gemini-2.0-flash

    specific years

    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
    ⓧ
    -1.01
     CreateTagHelper
    -0.83
     ویکی‌پدیای
    -0.82
    SequentialGroup
    -0.77
     esternos
    -0.76
     nakalista
    -0.73
    iNdEx
    -0.70
    UnusedPrivate
    -0.67
    Personendaten
    -0.66
     مشين
    -0.64
    POSITIVE LOGITS
     
    1.69
    2
    1.31
     २०
    1.01
     ۲۰۱
    0.92
     ২০১
    0.92
     FY
    0.86
     năm
    0.81
     ۲۰
    0.78
     ২০
    0.77
     vuonna
    0.74
    Activations Density 0.488%

    No Known Activations