© 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. 18-GEMMASCOPE-RES-16K
    11. 11746
    Prev
    Next
    INDEX
    Explanations

    expressions of deep emotions and sentiments related to loss and grief

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

    Mentioning or being unable to find the right words

    np_acts-logits-general · gemini-2.0-flash

    words aren't enough

    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
    RegressionTest
    -0.63
     विश्वसनीयता
    -0.59
    Lähteet
    -0.58
    UserScript
    -0.58
    coroutines
    -0.57
    InSection
    -0.57
    shadowRadius
    -0.56
    IsContent
    -0.54
    enderror
    -0.54
     Moq
    -0.54
    POSITIVE LOGITS
     words
    1.64
     Words
    1.53
    Words
    1.44
     WORDS
    1.30
    words
    1.25
     word
    1.11
     speechless
    1.10
    WORDS
    1.09
     palabras
    1.08
     Worte
    1.03
    Activations Density 0.126%

    No Known Activations