© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15573
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or actions within specific contexts

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

    Third-person pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    pronoun + verb

    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
    Doing
    -0.60
    oughlin
    -0.55
    doing
    -0.55
    Done
    -0.55
     Doing
    -0.55
    gway
    -0.54
    expandindo
    -0.51
    done
    -0.50
     Done
    -0.49
     Mucha
    -0.47
    POSITIVE LOGITS
     ComVisible
    0.72
    berdayakan
    0.65
    ArrowToggle
    0.63
    ReusableCell
    0.60
     belong
    0.60
    RegressionTest
    0.58
    ptest
    0.56
     dalamnya
    0.56
     aDecoder
    0.54
     belongs
    0.53
    Activations Density 0.177%

    No Known Activations