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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5213
    Prev
    Next
    INDEX
    Explanations

    terms related to "cross" concepts, especially in technical or scientific contexts

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

    "cross" or "cross-"

    np_acts-logits-general · gemini-2.0-flash

    cross- with hyphenated words

    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
    
    -0.76
    nonatomic
    -0.67
    upaten
    -0.62
    HostException
    -0.61
    PerformLayout
    -0.60
    PhysRevD
    -0.59
    execSQL
    -0.59
    ivir
    -0.59
    apyrus
    -0.58
    PhysRev
    -0.57
    POSITIVE LOGITS
     CROSS
    1.33
     cross
    1.32
    Cross
    1.28
     Cross
    1.27
    CROSS
    1.17
    cross
    1.16
     cros
    1.00
     crosses
    0.98
     Cros
    0.86
     Crossover
    0.85
    Activations Density 0.076%

    No Known Activations