© 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. 25-GEMMASCOPE-RES-16K
    11. 280
    Prev
    Next
    INDEX
    Explanations

    specific historical references to conflicts involving Soviet prisoners of war in Finland

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gatsby
    -0.65
     ivelany
    -0.57
    SharedCtor
    -0.55
    reis
    -0.54
     MonoBehaviour
    -0.53
     demografica
    -0.52
    LEncoder
    -0.52
    </tfoot>
    -0.50
    /**
    -0.49
    ScopeManager
    -0.48
    POSITIVE LOGITS
     conflict
    1.15
     battle
    1.11
     combat
    1.02
     battles
    1.01
     conflicts
    1.00
     combats
    0.97
     fighting
    0.95
    conflict
    0.94
     warfare
    0.94
     war
    0.93
    Activations Density 0.457%

    No Known Activations