© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal profiles or identity descriptions

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

    Appears before numbers or codes

    np_acts-logits-general · gemini-2.0-flash

    legal or technical contexts

    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
     שוליים
    -0.54
    AIL
    -0.53
    lasi
    -0.48
     chi̍t
    -0.47
    原始内容存档于
    -0.47
    例文帳に追加
    -0.46
     structurally
    -0.46
     verle
    -0.45
    近平
    -0.44
    onus
    -0.44
    POSITIVE LOGITS
    IUrlHelper
    0.76
    ConstraintMaker
    0.61
    InSection
    0.57
    GHIJKLM
    0.57
     Tamb
    0.53
    AlterField
    0.53
     Winaray
    0.52
    featureID
    0.52
     MainAxisSize
    0.52
     aquesta
    0.52
    Activations Density 0.057%

    No Known Activations