© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 74417
    Prev
    Next
    INDEX
    Explanations

    references to ancient Roman culture and institutions

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

    Roman Catholic and Roman history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.81
    IUrlHelper
    -0.66
    +#+#
    -0.63
    balleur
    -0.63
     Monfieur
    -0.60
    bobox
    -0.59
    providedIn
    -0.57
    endforeach
    -0.57
    ActionCreators
    -0.56
    InjectMocks
    -0.56
    POSITIVE LOGITS
     Roman
    0.87
     Rome
    0.82
    Roman
    0.78
    Rome
    0.72
     Romans
    0.67
     romanos
    0.63
     Roma
    0.60
     rome
    0.59
    罗马
    0.58
    ローマ
    0.58
    Activations Density 0.007%

    No Known Activations