Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6144
    Prev
    Next
    INDEX
    Explanations

    terms related to disturbance, disruption, or interference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lowe
    -0.63
     tertinggi
    -0.55
    rawDesc
    -0.54
     commerciaux
    -0.54
    findpost
    -0.54
     comerciales
    -0.53
     postav
    -0.53
     hvid
    -0.53
     kropp
    -0.52
    SqlClient
    -0.52
    POSITIVE LOGITS
     disturbance
    1.61
     disturbances
    1.56
     Disturb
    1.46
     disturbed
    1.45
     disruption
    1.43
     disruptions
    1.35
     disturb
    1.34
     disrupt
    1.29
     pertur
    1.28
    urbing
    1.27
    Activations Density 0.240%

    No Known Activations