© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8117
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific queen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     Qu
    -0.44
     appunto
    -0.43
    rungsseite
    -0.43
     Abra
    -0.43
    GTCX
    -0.43
    VersionUID
    -0.41
    oded
    -0.41
    SpringRunner
    -0.41
    ngdoc
    -0.40
    borderWidth
    -0.38
    POSITIVE LOGITS
     queen
    0.78
    Queen
    0.77
     QUEEN
    0.73
    QUEEN
    0.71
    queen
    0.69
     Queen
    0.66
     Königin
    0.56
     queens
    0.55
    Treatment
    0.53
    WebElementEntity
    0.53
    Activations Density 0.137%

    No Known Activations