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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7098
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal services and consultation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionMode
    -0.41
     nahilalakip
    -0.41
    喳
    -0.37
     compar
    -0.35
    NOTIFICATION
    -0.35
     فريبيس
    -0.33
     iNdEx
    -0.33
    bulos
    -0.32
     mis
    -0.32
     crash
    -0.32
    POSITIVE LOGITS
    WebServlet
    0.46
    TagMode
    0.46
    AndEndTag
    0.44
    achelors
    0.43
    +#+
    0.43
     Unsere
    0.41
    prepareStatement
    0.41
     vores
    0.40
    umentación
    0.40
     Databases
    0.39
    Activations Density 0.268%

    No Known Activations