© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 428
    Prev
    Next
    INDEX
    Explanations

    specific structural elements and formatting within technical documents

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

    introductory phrases or cues in questions related to various topics

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

    technical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.59
    httphttps
    -0.55
     مرئيه
    -0.53
     تانيه
    -0.52
    setupUi
    -0.50
    brando
    -0.47
    ürt
    -0.46
    toPromise
    -0.46
    терак
    -0.45
     Lij
    -0.44
    POSITIVE LOGITS
    OGND
    0.67
    Datuak
    0.66
     MonoBehaviour
    0.65
    ThemeOverlay
    0.65
     initComponents
    0.64
     JpaRepository
    0.63
    principalColumn
    0.61
     MyBatis
    0.59
    tanleria
    0.58
    VideoCapture
    0.58
    Activations Density 0.340%

    No Known Activations