© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13824
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "Who"

    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
    ensions
    -0.40
    кото
    -0.37
    ある
    -0.35
    陋
    -0.35
    emas
    -0.35
    ornata
    -0.35
     parallel
    -0.35
    ortes
    -0.35
    parentElement
    -0.34
    test
    -0.34
    POSITIVE LOGITS
     who
    3.06
     Who
    2.83
    Who
    2.81
    who
    2.69
     quien
    2.30
     quién
    2.20
     WHO
    2.02
    WHO
    1.96
    Quién
    1.95
     whom
    1.93
    Activations Density 0.140%

    No Known Activations