© 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. 8697
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating the subject of sentences

    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
     only
    -0.45
    слу
    -0.45
    eqn
    -0.43
    गी
    -0.43
     paid
    -0.43
     is
    -0.42
    The
    -0.42
    CHO
    -0.41
     makes
    -0.41
    didReceive
    -0.41
    POSITIVE LOGITS
    Hentet
    1.11
    RegressionTest
    1.07
    InjectAttribute
    1.00
    ьаж
    1.00
     resourceCulture
    0.98
    Geplaatst
    0.96
    LookAnd
    0.94
    StoryboardSegue
    0.93
    mybatisplus
    0.91
    expandindo
    0.90
    Activations Density 0.276%

    No Known Activations