© 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. 11974
    Prev
    Next
    INDEX
    Explanations

    phrases related to systems, design, and functionality

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

    preceding desirable outcomes

    np_acts-logits-general · gemini-2.0-flash

    enabling or preventing outcomes

    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
    Viited
    -0.83
    XmlAccessType
    -0.70
     lives
    -0.64
     refusé
    -0.61
     mourut
    -0.60
     الحره
    -0.60
     soprav
    -0.57
     voulait
    -0.57
     Lives
    -0.57
    المناصب
    -0.57
    POSITIVE LOGITS
     enables
    1.41
     allows
    1.37
     helps
    1.35
     ensures
    1.28
     prevents
    1.22
     reduces
    1.19
     enhances
    1.15
     causes
    1.15
     creates
    1.13
     gives
    1.12
    Activations Density 1.205%

    No Known Activations