© 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. 30-GEMMASCOPE-RES-16K
    6. 10536
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" and its variations in various contexts

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

    Tokens related to the word "drop"

    np_acts-logits-general · gemini-2.0-flash

    drop, dropped, dropping, drops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.61
    SequentialGroup
    -0.57
    UserScript
    -0.49
     protoimpl
    -0.48
    newBuilder
    -0.48
    qtype
    -0.46
    TemporalType
    -0.46
    MergeFrom
    -0.46
     sellado
    -0.46
     energías
    -0.46
    POSITIVE LOGITS
     drop
    1.47
     Drop
    1.41
    drop
    1.35
     dropped
    1.34
    Drop
    1.34
     DROP
    1.28
     dropping
    1.24
     drops
    1.19
    DROP
    1.18
     Dro
    1.16
    Activations Density 0.065%

    No Known Activations