© 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. 3702
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing experience or involvement in various activities

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

    Follows "been" or "has"

    np_acts-logits-general · gemini-2.0-flash

    has been VERB

    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
     appro
    -0.37
    Former
    -0.35
     zamanda
    -0.34
     aplicativo
    -0.32
     kasarigan
    -0.32
    msgTypes
    -0.32
    weise
    -0.31
     Affiliations
    -0.31
    Highly
    -0.30
    featureID
    -0.30
    POSITIVE LOGITS
    JspWriter
    0.61
    bcryptjs
    0.56
    ंदीखरीदारी
    0.54
    depuis
    0.53
     fince
    0.52
     autorytatywna
    0.51
     since
    0.50
     bestaan
    0.49
    since
    0.49
    lapsingToolbar
    0.49
    Activations Density 0.164%

    No Known Activations