© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13099
    Prev
    Next
    INDEX
    Explanations

    key phrases related to superiority and effectiveness in technology and products

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

    Preceding "go" or "way"

    np_acts-logits-general · gemini-2.0-flash

    designating the ideal or standard

    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
    NameInMap
    -0.75
    ंदीखरीदारी
    -0.61
    readdir
    -0.58
     initComponents
    -0.56
    TestingModule
    -0.54
    httphttps
    -0.52
    @
    -0.51
     BytesLike
    -0.51
    ωμα
    -0.50
    Clik
    -0.49
    POSITIVE LOGITS
     must
    1.04
    must
    0.91
     Must
    0.86
    Must
    0.83
     MUST
    0.83
     gold
    0.76
    脚注の使い方
    0.75
     king
    0.70
     jawaban
    0.69
    MUST
    0.69
    Activations Density 0.180%

    No Known Activations