© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84516
    Prev
    Next
    INDEX
    Explanations

    terms related to strengthening connections or relationships

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

    strengthen cooperation, relationship, efforts, or reforms

    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
    Parcelize
    -0.66
    LookAnd
    -0.66
    __((
    -0.60
     createState
    -0.60
    AutoField
    -0.59
     IBOutlet
    -0.59
    IsPostBack
    -0.59
    Slf
    -0.57
    principalColumn
    -0.56
    MarshalTo
    -0.56
    POSITIVE LOGITS
     strengthening
    1.69
    strengthen
    1.68
     strengthen
    1.68
    Strengthen
    1.66
     Strengthening
    1.59
     Strengthen
    1.54
     strengthens
    1.47
     strengthened
    1.45
     fortalecer
    1.15
     fortalec
    1.12
    Activations Density 0.003%

    No Known Activations