© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics in the context of films

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

    Financial or mathematical terms

    np_acts-logits-general · gemini-2.0-flash

    grossed amounts

    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
    __*/
    -0.63
    jspx
    -0.59
    brities
    -0.57
    webElementGuid
    -0.56
    ineno
    -0.48
    KURZBESCHREIBUNG
    -0.48
    profen
    -0.47
    Stateless
    -0.46
     play
    -0.46
    ChromeDriver
    -0.46
    POSITIVE LOGITS
     revenue
    0.99
     earnings
    0.91
     gross
    0.90
     revenues
    0.85
     income
    0.83
    revenue
    0.83
     yields
    0.79
     yield
    0.77
    gross
    0.76
     yielding
    0.75
    Activations Density 0.148%

    No Known Activations