Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9317
    Prev
    Next
    INDEX
    Explanations

    terms related to international military and political tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.49
    contentView
    -0.40
     person
    -0.36
     office
    -0.36
    hasError
    -0.35
    AVING
    -0.34
     judgment
    -0.34
     praco
    -0.33
     personal
    -0.33
     accountants
    -0.33
    POSITIVE LOGITS
    :✨
    0.69
     fieldNum
    0.64
    threat
    0.62
    ⤹
    0.59
     provoc
    0.59
     threat
    0.58
    ритори
    0.57
    vereignty
    0.57
     estekak
    0.56
     noDo
    0.54
    Activations Density 0.223%

    No Known Activations