© 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. 20-GEMMASCOPE-RES-131K
    11. 72575
    Prev
    Next
    INDEX
    Explanations

    chemical compound names, particularly those ending with "ium" or "monium"

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

    ending in ium

    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
     ainfi
    -0.56
     ſen
    -0.52
     électro
    -0.52
     poète
    -0.51
    utuhkan
    -0.51
     prédé
    -0.50
    wiſe
    -0.50
     juſ
    -0.50
     véri
    -0.49
     mystère
    -0.49
    POSITIVE LOGITS
    arium
    0.91
    um
    0.90
    lium
    0.84
    ium
    0.82
    inium
    0.76
    IUM
    0.76
    rium
    0.76
    dium
    0.75
    trum
    0.75
    inum
    0.75
    Activations Density 0.041%

    No Known Activations