© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7855
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.94
     فريبيس
    -0.91
     Theſe
    -0.85
     Мексичка
    -0.73
     GenerationType
    -0.70
    Controllo
    -0.69
    LayoutConstraint
    -0.67
     InputDecoration
    -0.64
     Jefus
    -0.64
    chaffung
    -0.63
    POSITIVE LOGITS
     nakalista
    0.57
     bumbu
    0.48
    gså
    0.45
     ordinaria
    0.43
     ugyan
    0.43
     ordinario
    0.42
    Tē
    0.41
    .
    0.41
    SuppressWarnings
    0.41
     ahogy
    0.40
    Activations Density 0.216%

    No Known Activations