© 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. 33-GEMMASCOPE-RES-16K
    6. 10479
    Prev
    Next
    INDEX
    Explanations

    keywords related to conflict, military actions, and personal attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.50
    Rptr
    -0.39
    RotationOrder
    -0.37
    MessageTagHelper
    -0.36
     dieux
    -0.35
    ecore
    -0.34
    เกี่ยว
    -0.34
     StatefulWidget
    -0.34
     encaje
    -0.32
     consigo
    -0.32
    POSITIVE LOGITS
     attack
    3.06
     attacks
    2.72
    attack
    2.64
     Attack
    2.55
     ATTACK
    2.52
     attacked
    2.47
    Attack
    2.41
     attacking
    2.34
     Attacks
    2.33
     ataque
    2.30
    Activations Density 0.484%

    No Known Activations