© 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. 31-GEMMASCOPE-RES-131K
    6. 110848
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-infective medications and their classifications

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

    medical prefixes starting with anti

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autowired
    -0.39
    Hentet
    -0.37
    onedDateTime
    -0.37
     للمعارف
    -0.36
     Kühlschrank
    -0.36
    Deactivate
    -0.35
    czegó
    -0.35
    logous
    -0.35
    TagNumber
    -0.35
    rección
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.55
     HIV
    0.54
     malaria
    0.54
     AspNetCore
    0.51
     cancer
    0.51
    quins
    0.50
     NSCoder
    0.47
     tumour
    0.47
     مشين
    0.46
     oxidizing
    0.46
    Activations Density 0.111%

    No Known Activations