© 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. 1-GEMMASCOPE-RES-16K
    6. 8339
    Prev
    Next
    INDEX
    Explanations

    terms related to properties and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انجليز
    -0.77
    FieldBuilder
    -0.68
     Montaigne
    -0.60
    AddTagHelper
    -0.58
    kolwiek
    -0.57
    EndInit
    -0.56
    yticks
    -0.56
    InSection
    -0.56
    aquin
    -0.55
    ValueStyle
    -0.55
    POSITIVE LOGITS
     properties
    4.09
     Properties
    3.69
    properties
    3.52
    Properties
    3.44
     PROPERTIES
    3.27
     property
    3.20
     Property
    2.75
    property
    2.75
     propiedades
    2.69
    PROPERTIES
    2.65
    Activations Density 0.086%

    No Known Activations