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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 14843
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "passage" and its variations

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

    passage and related words

    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
     inalámb
    -0.50
    หร
    -0.50
     Unidas
    -0.49
     Sociales
    -0.47
     femininas
    -0.46
     financieras
    -0.44
     líquida
    -0.44
    氢
    -0.43
     Suiza
    -0.43
     initComponents
    -0.43
    POSITIVE LOGITS
     passage
    1.36
     Passage
    1.34
    passage
    1.23
    Passage
    1.19
     passages
    1.19
     pasaje
    0.94
     passagem
    0.91
     Pass
    0.80
     passaggio
    0.75
     Passing
    0.74
    Activations Density 0.007%

    No Known Activations