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. 10790
    Prev
    Next
    INDEX
    Explanations

    terminology relating to evolution and advancements in various contexts

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

    ending in "ion", "al", and "ic"

    np_acts-logits-general · gemini-2.0-flash

    names of places and things

    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
     سكانية
    -0.97
     defaultstate
    -0.89
    Composable
    -0.82
    AddTagHelper
    -0.81
    ArrowToggle
    -0.77
    ContentAsync
    -0.77
    
    -0.76
     Italijanski
    -0.74
    ContentLoaded
    -0.73
    первых
    -0.73
    POSITIVE LOGITS
    teen
    1.16
    🏻
    1.06
    theless
    1.01
    ity
    1.00
    ous
    0.99
    🏼
    0.97
    ally
    0.96
    ation
    0.95
    ers
    0.95
    ism
    0.94
    Activations Density 1.522%

    No Known Activations