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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2798
    Prev
    Next
    INDEX
    Explanations

    references to enemies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doby
    -0.65
    prudence
    -0.64
     contamos
    -0.56
    Dunn
    -0.56
    lccn
    -0.54
    Portail
    -0.54
    au
    -0.54
     pedimos
    -0.53
    ш
    -0.53
     geschehen
    -0.52
    POSITIVE LOGITS
     Enemy
    1.27
     enemies
    1.23
     enemy
    1.20
     Enemies
    1.19
    Enemy
    1.06
    enemy
    1.04
     foes
    1.03
     opposes
    1.02
    enemies
    1.00
    Enemies
    1.00
    Activations Density 0.132%

    No Known Activations