© 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. 3-GEMMASCOPE-RES-16K
    6. 8716
    Prev
    Next
    INDEX
    Explanations

    keywords and details related to various job roles, requirements, and functions in tech and business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.28
     komende
    -0.26
      
    -0.26
     Thursday
    -0.26
     Wednesday
    -0.25
     Tuesday
    -0.25
     $
    -0.25
     
    -0.25
    uesday
    -0.25
     Jenderal
    -0.25
    POSITIVE LOGITS
    Diweddarwch
    0.88
     noDo
    0.84
     AssemblyCulture
    0.79
    UnusedPrivate
    0.71
    complexContent
    0.66
    thâu
    0.62
    yntaxException
    0.61
     PagesJaunes
    0.60
    tagHelperRunner
    0.60
    enderror
    0.60
    Activations Density 19.812%

    No Known Activations