© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8099
    Prev
    Next
    INDEX
    Explanations

    the repeated use of greetings and the word "big."

    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
     Balance
    -0.49
    Balance
    -0.47
    balance
    -0.45
     balance
    -0.44
     Equilibrium
    -0.41
    ValueGeneration
    -0.41
     vesti
    -0.41
    nowrap
    -0.40
    Equilibrium
    -0.39
    weave
    -0.39
    POSITIVE LOGITS
     Hi
    0.62
     Hey
    0.61
     cejas
    0.59
    Hi
    0.57
     <>",
    0.53
    Hey
    0.52
     montanha
    0.52
     promesas
    0.52
    phazard
    0.52
     GenerationType
    0.52
    Activations Density 0.068%

    No Known Activations