© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13285
    Prev
    Next
    INDEX
    Explanations

    references to trains or rail-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psum
    -0.44
     متحده
    -0.43
     Exacts
    -0.42
     Taktlose
    -0.41
     estekak
    -0.41
     للاسماء
    -0.40
    jsxFileName
    -0.39
    )))));
    -0.38
    toMatchSnapshot
    -0.38
     ErrIntOverflow
    -0.37
    POSITIVE LOGITS
     train
    3.23
     Train
    2.94
     trains
    2.86
     Trains
    2.64
    Train
    2.58
     railway
    2.44
     TRAIN
    2.42
    Trains
    2.34
    train
    2.33
     railroad
    2.30
    Activations Density 0.253%

    No Known Activations