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. 10035
    Prev
    Next
    INDEX
    Explanations

    specific programming and structural elements related to software or data organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    InitVars
    -0.60
     EClass
    -0.48
     först
    -0.43
    لمين
    -0.42
    odeficiency
    -0.42
     koszulka
    -0.41
    WriteBarrier
    -0.40
    ترة
    -0.39
     împ
    -0.39
    XmlAccessType
    -0.39
    POSITIVE LOGITS
    BeginContext
    0.82
    Sqft
    0.74
    expandindo
    0.73
     HasFactory
    0.66
    reactstrap
    0.66
     NgModule
    0.64
     الاطلاع
    0.58
    Personendaten
    0.58
    حياته
    0.58
    resave
    0.58
    Activations Density 0.050%

    No Known Activations