© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13864
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" and its variations, indicating a focus on actions related to dropping or falling

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

    "drop" or its variations

    np_acts-logits-general · gemini-2.0-flash

    dropping off

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     FirebaseAuth
    -0.52
    waitUntil
    -0.50
     DataTypes
    -0.48
     bezpeč
    -0.48
    FirebaseAuth
    -0.47
     Gestaltung
    -0.46
    setGeometry
    -0.46
     ſche
    -0.46
     réus
    -0.46
     VIAF
    -0.45
    POSITIVE LOGITS
    drop
    1.06
     drop
    0.98
     Drop
    0.93
    Drop
    0.92
     DROP
    0.88
     dropped
    0.88
     pick
    0.85
    dropped
    0.85
     pickup
    0.83
     Pickup
    0.82
    Activations Density 0.101%

    No Known Activations