© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14541
    Prev
    Next
    INDEX
    Explanations

    import statements related to specific Java packages

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

    Code, file paths, and URLs

    np_acts-logits-general · gemini-2.0-flash

    android, facebook, aws, intellij, google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.73
    fromnode
    -0.61
    rxjs
    -0.58
    __':
    -0.57
    LoadScene
    -0.57
    StoreMessageInfo
    -0.57
     @"/
    -0.55
    MergeFrom
    -0.54
    MenuView
    -0.53
     MenuView
    -0.53
    POSITIVE LOGITS
    google
    0.96
    fasterxml
    0.75
    sun
    0.69
    example
    0.68
    thought
    0.60
    alee
    0.59
    !*\
    0.57
     google
    0.56
    github
    0.55
    drew
    0.55
    Activations Density 0.049%

    No Known Activations