© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1107
    Prev
    Next
    INDEX
    Explanations

    instances of workplace disruption and negative interpersonal dynamics

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

    obstruction or disruption

    np_acts-logits-general · gemini-2.0-flash

    disruption and interference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شهاد
    -0.79
    ariste
    -0.52
    isNullOrEmpty
    -0.50
    gnąć
    -0.49
    LookAnd
    -0.49
    ituaries
    -0.47
    CppMethod
    -0.46
    ToSave
    -0.46
    SizeF
    -0.45
     resourceCulture
    -0.43
    POSITIVE LOGITS
     interfering
    1.78
     interference
    1.74
     interfere
    1.60
     Interference
    1.56
     interferes
    1.53
     disrupting
    1.51
    interference
    1.50
     disruptive
    1.48
     interrupting
    1.46
     distracting
    1.45
    Activations Density 0.550%

    No Known Activations