© 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. 20-GEMMASCOPE-RES-16K
    6. 11908
    Prev
    Next
    INDEX
    Explanations

    the presence of text formatting elements or specific structured markers in the document

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

    web archives or archiving

    np_acts-logits-general · gemini-2.0-flash

    internet archive

    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
     resourceCulture
    -0.86
     nahilalakip
    -0.83
    findpost
    -0.83
    تقاوى
    -0.82
    +#+#
    -0.79
    RegistryLite
    -0.79
    DebuggerNonUser
    -0.77
     مشين
    -0.75
    OGND
    -0.74
    ReusableCell
    -0.73
    POSITIVE LOGITS
     Wayback
    0.71
     Archive
    0.59
     оригіналу
    0.58
     web
    0.58
     archive
    0.58
    ARCH
    0.56
    Archive
    0.53
     preserve
    0.51
    Memento
    0.51
     original
    0.51
    Activations Density 0.055%

    No Known Activations