© 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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3299
    Prev
    Next
    INDEX
    Explanations

    instances of emotional interactions and physical touch between characters

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

    Comes before pronouns or punctuation

    np_acts-logits-general · gemini-2.0-flash

    plumes, snowflakes, sweat, sparks, tears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.46
    stateProvider
    -0.39
    enterOuterAlt
    -0.38
     resourceCulture
    -0.38
    yargs
    -0.37
     privately
    -0.37
    قایناق‌لار
    -0.37
     désolés
    -0.36
     kasarigan
    -0.36
    pertise
    -0.36
    POSITIVE LOGITS
     tears
    0.74
     plumes
    0.56
     snowflakes
    0.54
     Tears
    0.54
     lágrimas
    0.53
    tears
    0.52
    Tears
    0.51
    Sweat
    0.50
     odors
    0.50
     sparks
    0.50
    Activations Density 0.199%

    No Known Activations