© 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. 0-GEMMASCOPE-RES-16K
    11. 8953
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "grow" in different contexts

    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
     løpet
    -0.37
     bezig
    -0.35
     nødvendig
    -0.35
    ைக்
    -0.35
     něm
    -0.34
     nemoc
    -0.34
    Native
    -0.33
     včetně
    -0.33
     jiné
    -0.33
     būtų
    -0.31
    POSITIVE LOGITS
     Growth
    0.82
     Grow
    0.78
     Acti
    0.78
    Growth
    0.75
     المعيارى
    0.73
    activation
    0.72
     Activation
    0.72
     activating
    0.71
     Adults
    0.71
    存于互联网档案馆
    0.71
    Activations Density 0.320%

    No Known Activations