© 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. 18-GEMMASCOPE-RES-16K
    11. 4291
    Prev
    Next
    INDEX
    Explanations

    references to rankings or lists

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

    "top" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    Top lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filmografie
    -0.53
    MemoryWarning
    -0.51
    ograma
    -0.49
    laştır
    -0.49
    loroethene
    -0.48
    AnchorStyles
    -0.48
    eningen
    -0.47
    InstanceState
    -0.47
    صادر
    -0.46
     tranquille
    -0.46
    POSITIVE LOGITS
     TOP
    1.10
     tops
    1.00
     Tops
    0.97
    TOP
    0.94
     Top
    0.92
    notch
    0.92
     notch
    0.90
     tier
    0.88
     top
    0.87
    getTop
    0.84
    Activations Density 0.106%

    No Known Activations