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. 114466
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Dee" and related variations

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

    people's names starting with Dee

    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
    MathML
    -0.63
     Nugent
    -0.49
    LH
    -0.48
    xvii
    -0.47
    Martinez
    -0.47
    存于互联网档案馆
    -0.47
    ตร์
    -0.46
     Horowitz
    -0.45
    ՚
    -0.45
    hubarb
    -0.44
    POSITIVE LOGITS
     Dee
    2.59
    Dee
    2.25
     dee
    1.63
     DEE
    1.48
    dee
    1.39
    DEE
    1.15
     Deepak
    0.86
    dees
    0.82
    deemed
    0.75
     दी
    0.74
    Activations Density 0.004%

    No Known Activations