© 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. 24-GEMMASCOPE-RES-16K
    11. 7715
    Prev
    Next
    INDEX
    Explanations

    discussions about regulations, fairness, and governmental oversight in various contexts

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

    preceding negative financial terms

    np_acts-logits-general · gemini-2.0-flash

    overcharging or scams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    inobu
    -0.52
    ználat
    -0.51
     blossoms
    -0.51
    λων
    -0.49
    PerPage
    -0.49
     cdti
    -0.47
     createState
    -0.47
     abstracta
    -0.47
     febri
    -0.47
     ANGELES
    -0.46
    POSITIVE LOGITS
     gou
    1.04
     rip
    0.93
     charging
    0.88
     shady
    0.88
     ripped
    0.86
    Charging
    0.85
     ripping
    0.85
     scam
    0.85
     nickel
    0.85
    charging
    0.85
    Activations Density 0.289%

    No Known Activations