© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11089
    Prev
    Next
    INDEX
    Explanations

    expressions of effort and commitment to achieving the best outcomes

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

    phrases expressing effort or commitment to achieve or maintain something (such as "do our best," "do my best," "do her utmost").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.65
    SequentialGroup
    -0.64
    parsedMessage
    -0.61
     kasarigan
    -0.58
     Paglinawan
    -0.53
    orologio
    -0.51
    webElement
    -0.50
     يتيمه
    -0.49
    meyi
    -0.49
    RenderAtEndOf
    -0.49
    POSITIVE LOGITS
     best
    1.60
    best
    1.35
     Best
    1.20
    Best
    1.20
     BEST
    1.10
    BEST
    1.04
     terbaik
    1.01
     parha
    0.93
     beft
    0.92
     beste
    0.89
    Activations Density 0.167%

    No Known Activations