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. 20-GEMMASCOPE-RES-16K
    6. 11768
    Prev
    Next
    INDEX
    Explanations

    elements related to input and output streams in programming

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

    Java-related code or text

    np_acts-logits-general · gemini-2.0-flash

    System.currentTimeMillis()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.78
    ثيق
    -0.65
     intptr
    -0.63
     VIAF
    -0.63
    GTCX
    -0.63
    RTGC
    -0.62
     فريبيس
    -0.61
    енча
    -0.60
    ikyuu
    -0.60
     باخ
    -0.59
    POSITIVE LOGITS
     properties
    0.66
    System
    0.58
     Properties
    0.58
     property
    0.57
    PROP
    0.55
     System
    0.55
    properties
    0.55
     propiedades
    0.54
     Prop
    0.51
     getClass
    0.51
    Activations Density 0.251%

    No Known Activations