© 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. 4-GEMMASCOPE-RES-16K
    11. 15645
    Prev
    Next
    INDEX
    Explanations

    mentions of historical wars and military events, particularly focusing on World War II

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.86
    contentLoaded
    -0.68
    >{@
    -0.67
    XmlAccessType
    -0.64
    elemField
    -0.63
    }]
    -0.62
    IVEREF
    -0.62
     MenuView
    -0.61
    })->
    -0.60
    ThroughAttribute
    -0.60
    POSITIVE LOGITS
     WWII
    1.09
     war
    0.94
    大戦
    0.93
     Weltkrieg
    0.90
     wartime
    0.86
     War
    0.83
    war
    0.76
     Hitler
    0.71
    kriegs
    0.71
    War
    0.70
    Activations Density 0.287%

    No Known Activations