© 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. 10-GEMMASCOPE-RES-16K
    6. 12875
    Prev
    Next
    INDEX
    Explanations

    terms related to disruption or interference with normal processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.48
     braccia
    -0.47
    RetentionPolicy
    -0.47
    RTLU
    -0.45
    EndInit
    -0.45
    hoeddwyd
    -0.42
    isContained
    -0.41
     gambe
    -0.40
    sofá
    -0.40
     mourut
    -0.40
    POSITIVE LOGITS
     disrupted
    0.99
     disturbed
    0.93
     disrupt
    0.92
     disturb
    0.91
     disruption
    0.90
     disrupting
    0.87
     disturbance
    0.86
     Disturb
    0.82
     distur
    0.78
     spoiling
    0.77
    Activations Density 0.716%

    No Known Activations