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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 145
    Prev
    Next
    INDEX
    Explanations

    references to property and property-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "property"

    np_acts-logits-general · gemini-2.0-flash

    property damage, tax, rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.83
     Cæsar
    -0.81
     Tanja
    -0.81
    extAlignment
    -0.79
     cardiaque
    -0.77
     telefónica
    -0.77
    basicConfig
    -0.77
    withstanding
    -0.77
    BeginContext
    -0.76
     Anya
    -0.76
    POSITIVE LOGITS
     properties
    1.44
     property
    1.36
    getProperty
    1.28
     getProperty
    1.26
     Properties
    1.25
     Property
    1.25
    setProperty
    1.20
    properties
    1.18
     PROPERTY
    1.16
    property
    1.12
    Activations Density 0.079%

    No Known Activations