© 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. 2-GEMMASCOPE-RES-16K
    11. 12947
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to measurement and assessment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.91
    ContentAsync
    -0.85
     <<<<<<<<<<<<<<
    -0.84
    httphttps
    -0.82
    SharedCtor
    -0.81
    rungsseite
    -0.80
     kasarigan
    -0.80
    MigrationBuilder
    -0.79
     مشين
    -0.79
    WriteTagHelper
    -0.78
    POSITIVE LOGITS
     promote
    0.50
     identify
    0.50
     integrate
    0.49
     modify
    0.48
     collect
    0.47
    identify
    0.46
     pursue
    0.46
     establish
    0.46
     make
    0.46
     calculate
    0.45
    Activations Density 2.768%

    No Known Activations