© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10121
    Prev
    Next
    INDEX
    Explanations

    phrases related to weapons and their characteristics in contexts involving combat or fighting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ázaro
    -0.53
     Infórmanos
    -0.52
     Coney
    -0.50
    ándalo
    -0.49
    ratto
    -0.48
    ยาย
    -0.47
     papillon
    -0.46
    askin
    -0.45
     banc
    -0.45
    ėk
    -0.45
    POSITIVE LOGITS
     sword
    1.34
     swords
    1.22
    sword
    1.11
     Sword
    1.03
     Swords
    0.97
    Sword
    0.95
     knights
    0.94
     knight
    0.89
     warrior
    0.86
     espada
    0.85
    Activations Density 0.259%

    No Known Activations