© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 10005
    Prev
    Next
    INDEX
    Explanations

    references to battles or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alembic
    -0.47
     прико
    -0.46
    subpackage
    -0.44
     Privacy
    -0.44
     CGPoint
    -0.43
    Privacy
    -0.43
     ArrayAdapter
    -0.42
    ENSA
    -0.42
     Endocrine
    -0.41
     initComponents
    -0.41
    POSITIVE LOGITS
     battle
    1.33
     battles
    1.24
     fighting
    1.21
     fight
    1.18
     battling
    1.16
     battled
    1.16
    battle
    1.13
     fought
    1.13
    Fighting
    1.13
     BATTLE
    1.11
    Activations Density 1.876%

    No Known Activations