© 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. 9-GEMMASCOPE-RES-16K
    6. 9422
    Prev
    Next
    INDEX
    Explanations

    content related to educators and the education system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     operazioni
    -0.48
     عمليات
    -0.45
     Lombardo
    -0.41
     OPERATIONS
    -0.39
    Waga
    -0.39
    ethene
    -0.38
    uslar
    -0.38
     насељу
    -0.37
    Arco
    -0.36
     regioni
    -0.36
    POSITIVE LOGITS
     teacher
    1.86
     teachers
    1.80
     Teacher
    1.78
     Teachers
    1.78
    Teacher
    1.72
    Teachers
    1.66
    teacher
    1.65
     TEACHER
    1.65
     TEACHERS
    1.54
    teachers
    1.52
    Activations Density 0.126%

    No Known Activations