© 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. 3-GEMMASCOPE-RES-16K
    11. 15747
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "going" in various forms, indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -1.17
    TypedDataSet
    -1.07
    mybatisplus
    -1.07
    :✨
    -1.03
    ContentAsync
    -1.03
    RenderAtEndOf
    -1.02
    ValueStyle
    -0.99
     Efq
    -0.98
    LookAnd
    -0.97
     myſelf
    -0.97
    POSITIVE LOGITS
     will
    0.72
     Will
    0.60
     Nova
    0.59
     WILL
    0.57
     want
    0.55
     won
    0.54
     need
    0.53
    int
    0.53
     to
    0.51
     afin
    0.50
    Activations Density 0.064%

    No Known Activations