© 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. 11-GEMMASCOPE-RES-16K
    11. 8658
    Prev
    Next
    INDEX
    Explanations

    terms related to disruptions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     braço
    -0.39
     izman
    -0.32
     braços
    -0.32
     mengal
    -0.31
     BoxFit
    -0.31
     brazos
    -0.31
     onResponse
    -0.30
     death
    -0.30
     eneste
    -0.30
     morire
    -0.30
    POSITIVE LOGITS
     disturb
    1.22
     disturbance
    1.22
     Disturb
    1.17
     disturbances
    1.16
     disruption
    1.11
     distur
    1.11
     disturbed
    1.09
     disrupt
    1.03
     perturb
    1.02
     disruptions
    1.02
    Activations Density 0.485%

    No Known Activations