© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6494
    Prev
    Next
    INDEX
    Explanations

    references to properties and property management

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

    Text related to "property"

    np_acts-logits-general · gemini-2.0-flash

    property and its associated terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.89
    äher
    -0.83
    withstanding
    -0.80
     IBOutlet
    -0.76
     tartalomajánló
    -0.75
     colorés
    -0.70
     abbond
    -0.69
    ുകൾ
    -0.69
     telefónica
    -0.67
    揄
    -0.67
    POSITIVE LOGITS
     properties
    1.06
     getProperty
    1.05
     property
    0.95
    getProperty
    0.86
    PROPERTY
    0.85
    setProperty
    0.84
    properties
    0.84
    property
    0.83
     Properties
    0.83
     Property
    0.81
    Activations Density 0.084%

    No Known Activations