© 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. 2-GEMMASCOPE-RES-16K
    11. 15345
    Prev
    Next
    INDEX
    Explanations

    references to conflicts involving enemies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.73
     gynhyrchwyd
    -0.55
    Personendaten
    -0.55
    WebControls
    -0.54
    CloseOperation
    -0.53
     saites
    -0.53
     viewDidLoad
    -0.53
     olímp
    -0.52
     seguito
    -0.51
    PropertyChanging
    -0.51
    POSITIVE LOGITS
     enemy
    3.35
     enemies
    3.14
     Enemy
    3.00
    enemy
    2.91
     Enemies
    2.72
    Enemy
    2.62
    enemies
    2.60
    Enemies
    2.46
     ennemis
    2.15
     enemigo
    2.13
    Activations Density 0.119%

    No Known Activations