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. 3-GEMMASCOPE-RES-16K
    6. 8429
    Prev
    Next
    INDEX
    Explanations

    references to elite groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newOwner
    -0.52
    WebElementEntity
    -0.51
     jsPsych
    -0.51
     gonzález
    -0.50
     kapture
    -0.47
     tangan
    -0.46
     OFDb
    -0.46
    DispatchToProps
    -0.45
    hilangan
    -0.43
     propOrder
    -0.42
    POSITIVE LOGITS
     elite
    1.12
     differentiate
    0.98
     distinguish
    0.97
     Elite
    0.93
    elite
    0.92
    Elite
    0.91
     differentiated
    0.90
     elites
    0.90
     differentiates
    0.87
     differentiating
    0.83
    Activations Density 0.085%

    No Known Activations