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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5214
    Prev
    Next
    INDEX
    Explanations

    mentions of firearms and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Independiente
    -0.39
     znan
    -0.37
     artística
    -0.36
     despacho
    -0.34
     architet
    -0.33
     Arquitectura
    -0.33
    ftagPool
    -0.33
    Tembelea
    -0.33
     artístico
    -0.33
     Paglinawan
    -0.33
    POSITIVE LOGITS
     pistols
    0.83
     firearms
    0.81
     firearm
    0.81
     pistol
    0.81
    guns
    0.80
     Firearms
    0.77
     handgun
    0.77
     rifle
    0.75
     rifles
    0.73
     guns
    0.69
    Activations Density 0.059%

    No Known Activations