© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4826
    Prev
    Next
    INDEX
    Explanations

    important terms related to business operations and service disruptions

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

    words related to negative consequences, failures, or damages.

    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
     bénévol
    -0.31
    NXG
    -0.30
     modesty
    -0.29
    iedenen
    -0.29
    Legături
    -0.29
    даль
    -0.29
    zzati
    -0.28
    */].
    -0.28
     espan
    -0.28
     فار
    -0.28
    POSITIVE LOGITS
     disruption
    1.52
     disruptions
    1.45
     interruption
    1.29
     interruptions
    1.26
     disrupted
    1.23
     shutdown
    1.23
     downtime
    1.19
     disrupting
    1.17
     disrupt
    1.15
     outage
    1.13
    Activations Density 0.366%

    No Known Activations