© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions relating to properties of sets, including their dimensions and relationships

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    is followed by descriptive properties

    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
     unfamiliar
    -0.60
    cshtml
    -0.58
    +#+#
    -0.55
    낌
    -0.55
     Uncertain
    -0.55
     Pristupljeno
    -0.52
    unusual
    -0.52
     Compar
    -0.52
     grappling
    -0.52
     ungewöhn
    -0.51
    POSITIVE LOGITS
    ódó
    0.62
     brancas
    0.62
    Scénario
    0.60
     Puoi
    0.57
     Protestantism
    0.56
     eux
    0.55
     orina
    0.54
    LookAnd
    0.53
    ffindor
    0.53
     femei
    0.53
    Activations Density 1.261%

    No Known Activations