© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1308
    Prev
    Next
    INDEX
    Explanations

    conceptual connections and relationships involving collaboration and agreements

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

    the word "agreement" and related words about formal arrangements or contracts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.58
    InitVars
    -0.47
    IUrlHelper
    -0.47
    Ӕ
    -0.46
     ActivatedRoute
    -0.46
     mitu
    -0.46
    imir
    -0.44
    Дереккөздер
    -0.44
     tiguan
    -0.44
     Schna
    -0.43
    POSITIVE LOGITS
     with
    1.30
    กับ
    1.26
     auprès
    1.09
     contigo
    0.84
     kanssa
    0.81
     comigo
    0.79
     với
    0.78
     conmigo
    0.75
     bersama
    0.74
     עם
    0.68
    Activations Density 0.717%

    No Known Activations