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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 4581
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface controls and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -1.04
    GEBURTSDATUM
    -1.03
     فريبيس
    -0.90
    Abitanti
    -0.89
     Италијани
    -0.88
    IUrlHelper
    -0.87
    webElement
    -0.86
    ніципалі
    -0.85
    InitVars
    -0.82
    Personensuche
    -0.82
    POSITIVE LOGITS
    ResumeLayout
    2.22
    EndInit
    0.59
    tér
    0.46
    talt
    0.42
     például
    0.41
    ければ
    0.39
     esimerkiksi
    0.39
     false
    0.38
    куда
    0.38
     False
    0.38
    Activations Density 0.006%

    No Known Activations