© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 783
    Prev
    Next
    INDEX
    Explanations

    easily performed actions or processes

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

    Follows "easily" (or translations of "easily")

    np_acts-logits-general · gemini-2.0-flash

    easily followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.67
    ьаж
    -0.66
    Билгалдахарш
    -0.65
    +#+#
    -0.64
    rungsseite
    -0.63
    __':
    -0.62
    UserScript
    -0.60
    __":
    -0.59
    ſelf
    -0.57
    NewLabel
    -0.57
    POSITIVE LOGITS
     easily
    1.67
    easily
    1.62
    Easily
    1.56
     Easily
    1.54
     fácilmente
    1.33
     facilmente
    1.26
     facilement
    1.20
     readily
    1.05
     легко
    0.93
     quickly
    0.92
    Activations Density 0.197%

    No Known Activations