© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12619
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and code structure

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

    Code snippets using "System" or "Unity"

    np_acts-logits-general · gemini-2.0-flash

    game development engine unity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.63
    TemporalType
    -0.57
     kasarigan
    -0.57
     beginnetje
    -0.55
    MessageState
    -0.55
    antası
    -0.55
     noqa
    -0.53
    AnchorStyles
    -0.53
    elemField
    -0.52
    tershire
    -0.51
    POSITIVE LOGITS
     UnityEngine
    0.50
     jsPsych
    0.35
    ')")
    0.31
     MonoBehaviour
    0.31
    pushFollow
    0.30
     венти
    0.29
    Véxase
    0.29
    leyebilirsiniz
    0.29
     Script
    0.28
     referrerpolicy
    0.28
    Activations Density 0.048%

    No Known Activations