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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 113678
    Prev
    Next
    INDEX
    Explanations

    words related to greetings and expressions of welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    greeting others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.42
     TableColumn
    -0.41
    tabPage
    -0.38
     StatefulWidget
    -0.38
     newData
    -0.38
    *}$
    -0.38
     UserManager
    -0.38
     macchine
    -0.37
    *$
    -0.36
    TableViewCell
    -0.36
    POSITIVE LOGITS
     greeting
    2.19
     Greeting
    2.11
    Greeting
    2.09
    greeting
    2.05
     greetings
    1.88
     Greetings
    1.77
     greet
    1.66
    Greetings
    1.63
    greetings
    1.58
    greet
    1.52
    Activations Density 0.002%

    No Known Activations