© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 43043
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" and its variations indicating a decrease or removal

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

    drop people or drop out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.55
    Życiorys
    -0.53
    AndEndTag
    -0.48
     noqa
    -0.47
    UserScript
    -0.46
    ftagPool
    -0.45
     sellado
    -0.45
    /**
    -0.44
    kulum
    -0.42
    DockStyle
    -0.42
    POSITIVE LOGITS
     dropped
    1.21
     drop
    1.16
     dropping
    1.12
     Drop
    1.11
    Drop
    1.03
     DROP
    1.02
     drops
    1.00
    drop
    1.00
    dropped
    0.98
    dropping
    0.97
    Activations Density 0.013%

    No Known Activations