© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10428
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to administrative and academic positions

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

    professional titles and organizational positions in formal documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     للمعارف
    -0.93
     Италијани
    -0.81
    NameInMap
    -0.74
     disambiguazione
    -0.74
     Infórmanos
    -0.71
     насељу
    -0.63
    rungsseite
    -0.62
     autorytatywna
    -0.61
     Exacts
    -0.61
     يتيمه
    -0.60
    POSITIVE LOGITS
     coordinator
    0.46
     producer
    0.46
     editor
    0.44
     director
    0.41
    maker
    0.41
    producer
    0.39
     consultant
    0.38
     maker
    0.38
     supervisor
    0.38
     designer
    0.38
    Activations Density 0.184%

    No Known Activations