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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86681
    Prev
    Next
    INDEX
    Explanations

    instances of physical ailments and health-related conditions

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

    unable to, his deceased, couple jointly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     hombros
    -0.35
     généralement
    -0.32
    .
    -0.30
     bersama
    -0.30
     disfruta
    -0.29
    S
    -0.29
     údaje
    -0.28
     todavía
    -0.28
     generally
    -0.28
     now
    -0.27
    POSITIVE LOGITS
     ब्रेकडाउन
    0.98
    tagHelperRunner
    0.98
     betweenstory
    0.96
     defaultstate
    0.91
     Normdatei
    0.91
    SharedDtor
    0.89
     незавершена
    0.88
    ſſung
    0.88
     OFDb
    0.87
    InputBorder
    0.87
    Activations Density 0.065%

    No Known Activations