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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1064
    Prev
    Next
    INDEX
    Explanations

    references to methadone in relation to its usage, effects, and considerations for treatment

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

    methadone usage and safety

    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
     pinulongan
    -0.63
    rungsseite
    -0.61
     незавершена
    -0.59
    ViewImports
    -0.57
     BoxFit
    -0.57
    exitRule
    -0.57
    MessageOf
    -0.56
     kasarigan
    -0.56
    ]--;
    -0.52
    ufficio
    -0.52
    POSITIVE LOGITS
     Dhoni
    0.80
     Minaj
    0.61
    adone
    0.60
     Lohan
    0.58
     Lovato
    0.56
     Cena
    0.54
     Luffy
    0.54
    ishw
    0.52
     Maradona
    0.50
     Najib
    0.49
    Activations Density 0.004%

    No Known Activations