© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5885
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accident."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahu
    -0.58
    )<\
    -0.56
    matory
    -0.54
    ractable
    -0.53
    mew
    -0.51
    CWE
    -0.50
    mius
    -0.49
     ujednoznacz
    -0.49
    SPIRE
    -0.49
    fice
    -0.49
    POSITIVE LOGITS
    accident
    0.91
     accident
    0.88
     folder
    0.84
     Accident
    0.81
     folders
    0.81
    ViewController
    0.80
     Folder
    0.72
    انجليز
    0.71
     Audiodateien
    0.69
    Accident
    0.68
    Activations Density 0.048%

    No Known Activations