© 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. 13147
    Prev
    Next
    INDEX
    Explanations

    references to cultural immersion and engagement

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

    Opportunities to experience or see things directly

    np_acts-logits-general · gemini-2.0-flash

    direct firsthand experience

    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
    脚注の使い方
    -0.87
     henvis
    -0.67
    withIdentifier
    -0.59
    abinieri
    -0.56
    ียง
    -0.50
    parate
    -0.49
    roek
    -0.48
    ∬
    -0.47
    trise
    -0.47
    manjaro
    -0.47
    POSITIVE LOGITS
     firsthand
    1.94
     directly
    1.29
     direttamente
    1.19
     direct
    1.17
    directly
    1.16
     langsung
    1.14
     intimately
    1.12
     directamente
    1.10
     personally
    1.10
     directement
    1.09
    Activations Density 0.287%

    No Known Activations