© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4881
    Prev
    Next
    INDEX
    Explanations

    words related to emotional expression and sensitivity

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

    ending in "ly", "ous", "ish", "tive", or "able"

    np_acts-logits-general · gemini-2.0-flash

    adverbs ending in -ly

    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
    Karriere
    -0.48
     rental
    -0.44
     Rental
    -0.41
    ordnet
    -0.41
     recruiting
    -0.40
     مجرد
    -0.39
     Peters
    -0.39
     lett
    -0.39
     Reset
    -0.38
     panela
    -0.38
    POSITIVE LOGITS
    vellous
    0.53
    ously
    0.49
    edly
    0.49
     uncon
    0.49
    EDEFAULT
    0.48
    SuppressLint
    0.48
     ottim
    0.48
    tagHelperRunner
    0.48
    bly
    0.48
    ingly
    0.47
    Activations Density 0.385%

    No Known Activations