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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2675
    Prev
    Next
    INDEX
    Explanations

    elements related to chart and data structures in programming or API documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endswith
    -0.45
    getResultList
    -0.45
    Obrázky
    -0.43
    ysacchar
    -0.40
    allowNull
    -0.40
    DebuggerNonUser
    -0.40
    <eos>
    -0.39
    dbo
    -0.39
    假
    -0.39
    AVC
    -0.38
    POSITIVE LOGITS
     useAppContext
    0.88
     تضيفلها
    0.86
    GraphicsUnit
    0.79
    Према
    0.77
    MemoryWarning
    0.76
    AndroidJUnit
    0.75
    ConstraintMaker
    0.74
    évaluateur
    0.72
     ComVisible
    0.71
     CommonModule
    0.68
    Activations Density 0.360%

    No Known Activations