© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1470
    Prev
    Next
    INDEX
    Explanations

    references to problematic social behaviors, particularly related to toxic workplace dynamics

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

    references to toxic social behaviors and relationships in workplaces

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

    petty complaints and gossip

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    XmlAccessType
    -0.66
     utafitiHapana
    -0.62
    MLLoader
    -0.58
    ocities
    -0.56
    __*/
    -0.54
     BoxFit
    -0.54
    adel
    -0.53
     propOrder
    -0.53
    GenerationType
    -0.52
    complexType
    -0.52
    POSITIVE LOGITS
     gossi
    0.96
     gossip
    0.94
     complaining
    0.84
    Gossip
    0.80
    gossip
    0.78
     Gossip
    0.76
     complain
    0.74
    complain
    0.67
     nagging
    0.64
     quarrels
    0.63
    Activations Density 0.181%

    No Known Activations