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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68883
    Prev
    Next
    INDEX
    Explanations

    expressions of sincerity or emphasis related to truthfulness

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

    intensifier "truly"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.52
    Хьажоргаш
    -0.52
     fubject
    -0.49
     թվական
    -0.45
     Houſe
    -0.43
     BorderSide
    -0.42
     armes
    -0.42
     normales
    -0.42
     Dispose
    -0.42
    Sink
    -0.42
    POSITIVE LOGITS
    truly
    1.16
     truly
    1.16
    Truly
    1.05
     Truly
    1.02
     REALLY
    0.81
     verdaderamente
    0.79
    really
    0.77
     really
    0.75
     Really
    0.71
     gerçekten
    0.71
    Activations Density 0.005%

    No Known Activations