Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13356
    Prev
    Next
    INDEX
    Explanations

    references to various kings and monarchs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whistler
    -0.66
     Zacks
    -0.58
    PickerController
    -0.58
    CloseOperation
    -0.57
     Hawke
    -0.57
     Travis
    -0.56
    indicato
    -0.56
    UrlResolution
    -0.55
    älä
    -0.53
    AddTagHelper
    -0.52
    POSITIVE LOGITS
     King
    1.07
     Kings
    1.06
     KING
    1.00
     kings
    0.97
     king
    0.92
    King
    0.90
    Kings
    0.89
     Queen
    0.85
     Koenig
    0.84
    👑
    0.81
    Activations Density 0.107%

    No Known Activations