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. 3-GEMMASCOPE-RES-16K
    6. 16293
    Prev
    Next
    INDEX
    Explanations

    references to weapons and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.88
    mergeFrom
    -0.84
    MigrationBuilder
    -0.82
     Insured
    -0.72
    
    -0.72
     lynx
    -0.71
     مشين
    -0.70
    postIndex
    -0.70
    webElementXpaths
    -0.69
     NSCoder
    -0.69
    POSITIVE LOGITS
     weapons
    2.85
     weapon
    2.71
     Weapon
    2.47
     Weapons
    2.44
    weapons
    2.37
    weapon
    2.34
    Weapons
    2.16
    Weapon
    2.14
     weaponry
    1.89
    武器
    1.73
    Activations Density 0.048%

    No Known Activations