© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8006
    Prev
    Next
    INDEX
    Explanations

    references to members of parliament and related political terminology

    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
    couvrez
    -0.40
    DeleteBehavior
    -0.38
     justicia
    -0.36
    ขอบ
    -0.36
     incomplète
    -0.36
    Preference
    -0.36
     vissza
    -0.36
     kenal
    -0.35
     harvest
    -0.35
     obno
    -0.35
    POSITIVE LOGITS
     MP
    1.21
    MP
    1.02
     MPs
    1.00
     mp
    0.96
     Mp
    0.84
    Mp
    0.73
     Bluetooth
    0.66
     iPod
    0.64
    MPN
    0.63
    mp
    0.60
    Activations Density 0.121%

    No Known Activations