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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113932
    Prev
    Next
    INDEX
    Explanations

    references to loyalty and allegiance, particularly related to the Union during the Civil War

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

    Union conflict and government action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.56
    sidemargin
    -0.52
    RectangleBorder
    -0.51
    adpleegd
    -0.45
    bootstrapcdn
    -0.44
    Einzelnachweise
    -0.40
    inSlope
    -0.40
     Obrador
    -0.39
    InjectAttribute
    -0.39
    achios
    -0.38
    POSITIVE LOGITS
    kwds
    0.45
    TRIBUN
    0.44
    Clik
    0.42
     betweenstory
    0.41
    ItemBackground
    0.40
    onsor
    0.38
    willReturn
    0.38
    ScopeManager
    0.37
     magistrates
    0.37
    Zeneca
    0.36
    Activations Density 0.086%

    No Known Activations