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. 9-GEMMASCOPE-RES-131K
    6. 83454
    Prev
    Next
    INDEX
    Explanations

    references to sulfur and its various compounds

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

    sulfur dioxide and cycles

    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
    piece
    -0.44
     pab
    -0.39
    teles
    -0.38
     telescopic
    -0.38
    a
    -0.37
     teles
    -0.37
    actual
    -0.37
    先
    -0.37
     Jee
    -0.37
     Neale
    -0.36
    POSITIVE LOGITS
     sulfur
    2.06
     Sulfur
    1.98
     Sulphur
    1.94
    Sulfur
    1.92
     sulphur
    1.81
    phur
    1.41
    sulf
    1.36
     SUL
    1.10
     sulfu
    1.09
     sulf
    1.08
    Activations Density 0.012%

    No Known Activations