© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7202
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and self-identity

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

    "proud" or related terms

    np_acts-logits-general · gemini-2.0-flash

    proud to, pride of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnsafeEnabled
    -0.73
     CreateTagHelper
    -0.70
     mercies
    -0.63
     TestBed
    -0.62
     travelers
    -0.59
    complexContent
    -0.58
    Suara
    -0.58
     resourceCulture
    -0.58
    mapTo
    -0.57
     transfieras
    -0.57
    POSITIVE LOGITS
     proud
    1.64
    proud
    1.56
     Proud
    1.56
    Proud
    1.52
     pride
    1.49
     orgull
    1.47
     proudly
    1.35
     stolz
    1.28
     orgullo
    1.28
    pride
    1.26
    Activations Density 0.042%

    No Known Activations