© 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
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9360
    Prev
    Next
    INDEX
    Explanations

    references to healthcare professionals and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jooq
    -0.44
    号
    -0.38
     pening
    -0.38
    habhar
    -0.38
     kurulan
    -0.37
     рассе
    -0.37
     виправивши
    -0.37
    接
    -0.36
    solving
    -0.36
    Qualifier
    -0.35
    POSITIVE LOGITS
     administrators
    0.85
     teachers
    0.79
     journalists
    0.79
     technicians
    0.77
     staff
    0.77
     physicians
    0.76
     managers
    0.76
     assistants
    0.74
     policemen
    0.73
     secretaries
    0.73
    Activations Density 0.585%

    No Known Activations