Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2563
    Prev
    Next
    INDEX
    Explanations

    elements and syntax related to file paths or URLs

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

    Tokens containing "/" symbol

    np_acts-logits-general · gemini-2.0-flash

    slash or administrative

    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
     esternos
    -1.11
     itſelf
    -0.98
     ་་
    -0.95
     uſed
    -0.92
     crdi
    -0.92
     Efq
    -0.91
     doubtnut
    -0.90
     myſelf
    -0.89
     ―――――
    -0.89
     Monfieur
    -0.87
    POSITIVE LOGITS
    ˈ
    0.82
     /
    0.73
     Rosenthal
    0.68
     Her
    0.67
    evo
    0.64
     u
    0.64
     McCabe
    0.64
     Se
    0.64
     Ko
    0.63
    ininger
    0.63
    Activations Density 0.403%

    No Known Activations