© 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. 24-GEMMASCOPE-RES-16K
    11. 13853
    Prev
    Next
    INDEX
    Explanations

    instances of the word "top" or variations of it, particularly in ranking contexts

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

    Following "Top" or a hyphen

    np_acts-logits-general · gemini-2.0-flash

    top followed by category or ranking

    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
     فريبيس
    -0.64
    StoreMessageInfo
    -0.62
    Personensuche
    -0.59
    emang
    -0.58
     Exacts
    -0.57
    MockMvc
    -0.57
    AnchorStyles
    -0.57
    stanz
    -0.56
    AccessorTable
    -0.55
    PropertyChanging
    -0.52
    POSITIVE LOGITS
    notch
    1.00
     notch
    1.00
    most
    0.89
     tier
    0.86
     rated
    0.81
    flight
    0.79
    knot
    0.77
     priority
    0.75
    ically
    0.73
    secret
    0.73
    Activations Density 0.076%

    No Known Activations