© 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 - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6467
    Prev
    Next
    INDEX
    Explanations

    mentions of managerial transitions or leadership changes within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.90
    HostException
    -0.84
    HideFlags
    -0.73
     theaters
    -0.73
    ReusableCell
    -0.71
    XmlAccessType
    -0.71
     esternos
    -0.70
     ModelExpression
    -0.69
     theater
    -0.69
    ✨:
    -0.69
    POSITIVE LOGITS
    Singapore
    0.80
     Singapore
    0.79
     Malaysia
    0.74
    Malaysia
    0.65
    letar
    0.63
    APORE
    0.63
     LUMP
    0.59
     Defence
    0.58
    WebElementEntity
    0.55
    AYSIA
    0.54
    Activations Density 0.222%

    No Known Activations