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. 5-GEMMASCOPE-RES-16K
    6. 3716
    Prev
    Next
    INDEX
    Explanations

    instances of disturbance or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SqlClient
    -0.63
    spira
    -0.55
    ForValue
    -0.54
     Lowe
    -0.54
    vyšší
    -0.53
     brugt
    -0.53
    acre
    -0.50
     død
    -0.50
    balanceOf
    -0.49
     brukt
    -0.48
    POSITIVE LOGITS
     Disturb
    1.79
     disturbance
    1.75
     disturbed
    1.70
     disturbances
    1.70
     disturb
    1.65
     disruption
    1.61
     disrupted
    1.55
     disruptions
    1.55
     disrupt
    1.55
     disrupting
    1.48
    Activations Density 0.239%

    No Known Activations