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. 1-GEMMASCOPE-RES-16K
    6. 13373
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hear" in various contexts

    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
    Datuak
    -0.58
    页面存档备份
    -0.55
    JvmStatic
    -0.53
    PageFactory
    -0.53
    かわらず
    -0.52
    RetentionPolicy
    -0.51
    ttino
    -0.50
    AlterField
    -0.50
    iredo
    -0.49
    Mediabestanden
    -0.48
    POSITIVE LOGITS
     hear
    4.82
     hears
    4.06
     Hear
    4.01
    Hear
    3.76
     HEAR
    3.74
    hear
    3.61
     heard
    3.50
     hearing
    3.48
     Hearing
    3.02
    hearing
    2.99
    Activations Density 0.068%

    No Known Activations