© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5580
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to optimization and efficiency in engineering and computing

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

    phrases related to improving or increasing performance, capabilities, or effectiveness.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words indicating improvement, enhancement, or increased capability/performance.

    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
     فريبيس
    -0.60
    ActionCreators
    -0.46
    重さ
    -0.46
     PLWABN
    -0.45
     intptr
    -0.44
     Administrativna
    -0.44
    ImageContext
    -0.43
    writerow
    -0.43
    parsedMessage
    -0.42
    TargetException
    -0.42
    POSITIVE LOGITS
     considerably
    1.17
     significantly
    1.16
     drastically
    1.05
     substantially
    1.05
     dramatically
    1.02
     markedly
    0.95
     appreciably
    0.92
     further
    0.91
     erheblich
    0.90
     greatly
    0.88
    Activations Density 0.592%

    No Known Activations