© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121915
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "difference."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     embarc
    -0.52
    <blockquote>
    -0.41
     nocturno
    -0.40
     Consultez
    -0.40
     calendrier
    -0.40
    capai
    -0.37
     Câmara
    -0.37
     Verantwort
    -0.37
    bgcolor
    -0.37
     macetas
    -0.37
    POSITIVE LOGITS
     Difference
    1.24
     difference
    1.17
    Difference
    1.16
    difference
    1.16
     DIFFERENCE
    1.05
     differences
    0.96
     Differences
    0.91
    differences
    0.89
    Differences
    0.86
     verschil
    0.86
    Activations Density 0.020%

    No Known Activations