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. 18-GEMMASCOPE-RES-16K
    6. 15238
    Prev
    Next
    INDEX
    Explanations

    references to professional wrestling and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following tokens are prepositions or beginnings-of-sentences

    np_acts-logits-general · gemini-2.0-flash

    wrestling and combat sports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.55
    akes
    -0.54
     electrode
    -0.53
    burgo
    -0.52
     consola
    -0.52
    brtc
    -0.51
     verbe
    -0.51
    clav
    -0.50
    ctrons
    -0.50
     minerales
    -0.49
    POSITIVE LOGITS
     WWE
    1.00
     wrestling
    0.91
     Wrestling
    0.91
     wrestlers
    0.87
    WWE
    0.86
     wrestler
    0.86
    Wrestling
    0.84
     gimmick
    0.72
     AEW
    0.72
     wwe
    0.70
    Activations Density 0.064%

    No Known Activations