© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13999
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to action and movement

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

    leaving or fleeing

    np_acts-logits-general · gemini-2.0-flash

    departure and leaving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioutil
    -0.61
    UnusedPrivate
    -0.54
    prepareStatement
    -0.52
     surla
    -0.52
    ::_('
    -0.50
     հղումներ
    -0.50
    pushFollow
    -0.50
     mapStateToProps
    -0.50
     فريبيس
    -0.47
    tagHelperRunner
    -0.47
    POSITIVE LOGITS
     departing
    1.17
     departure
    1.15
     leaving
    1.12
     departs
    1.08
     depart
    1.06
     leave
    1.05
     departed
    1.04
     Leaving
    1.02
    Leaving
    0.98
    离去
    0.98
    Activations Density 0.384%

    No Known Activations