© 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. 0-GEMMASCOPE-RES-16K
    6. 10073
    Prev
    Next
    INDEX
    Explanations

    words associated with intelligence and cleverness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikiseite
    -0.58
     referrerpolicy
    -0.53
    rungsseite
    -0.52
     Reverso
    -0.51
     nahilalakip
    -0.50
     whither
    -0.47
    ̈́
    -0.47
     насељу
    -0.46
    ungkinkan
    -0.46
     bookseller
    -0.46
    POSITIVE LOGITS
     smart
    0.72
    Smart
    0.66
    smart
    0.65
     listening
    0.58
    orn
    0.55
     Smart
    0.54
    ش
    0.53
    Listening
    0.50
     listens
    0.48
     dumb
    0.48
    Activations Density 0.371%

    No Known Activations