© 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. 24-GEMMASCOPE-RES-16K
    6. 100
    Prev
    Next
    INDEX
    Explanations

    expressions related to accountability and civic responsibility

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

    Addressing or acknowledging a group of people

    np_acts-logits-general · gemini-2.0-flash

    addressing consumers or fans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.47
    MockBean
    -0.40
     tæ
    -0.40
     MainAxisSize
    -0.40
     merid
    -0.36
     Jinping
    -0.35
    NewUrlParser
    -0.35
    Портал
    -0.35
    Coordonnées
    -0.35
    讓他
    -0.34
    POSITIVE LOGITS
     fans
    0.82
     consumers
    0.81
    fans
    0.75
     users
    0.73
     customers
    0.72
     voters
    0.71
    Fans
    0.71
    民众
    0.64
     pelanggan
    0.64
     Fans
    0.64
    Activations Density 0.523%

    No Known Activations