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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 63249
    Prev
    Next
    INDEX
    Explanations

    references to monsters or monstrous beings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    monsters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🔙
    -0.59
    AxisAlignment
    -0.49
    addGap
    -0.49
    onResume
    -0.48
    ()")
    -0.47
    =>'
    -0.46
    ایج
    -0.46
    ayage
    -0.46
     reflexionar
    -0.45
    曖昧さ回避
    -0.45
    POSITIVE LOGITS
     monster
    1.14
    monster
    1.07
     Monster
    1.05
     monstre
    1.00
     monsters
    0.98
    Monster
    0.92
     Monsters
    0.90
    monsters
    0.89
     monstruo
    0.77
    Monsters
    0.76
    Activations Density 0.006%

    No Known Activations